INDEX

Explanations

phrases indicating action or involvement in events or developments

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

reet

-0.15

Ali

-0.15

 practical

-0.15

_TLS

-0.15

 Alic

-0.14

 Operating

-0.14

 SORT

-0.14

punk

-0.14

 regulator

-0.14

ads

-0.14

POSITIVE LOGITS

ibus

0.15

ÄŁÄ±nÄ±

0.14

dry

0.14

ãĥ¼ãĥį

0.14

 birthday

0.14

omaly

0.14

 FormData

0.14

.trip

0.14

morgan

0.14

aises

0.14

Activations Density 0.009%

phrases indicating action or involvement in events or developments

No Comments

No Known Activations