INDEX

Explanations

content related to sources and references in articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

mouth

-0.14

ear

-0.14

antan

-0.14

spot

-0.14

Ð»Ð¸Ñĩ

-0.14

 vict

-0.14

ãĤīãģļ

-0.13

etros

-0.13

WN

-0.13

POSITIVE LOGITS

Cin

0.16

ardi

0.16

ãĥ¡ãĥ³ãĥĪ

0.15

ioni

0.14

PACE

0.14

 hÃ£

0.14

ãĤ«ãĥ¼

0.14

ishi

0.14

é¨

0.13

.chomp

0.13

Activations Density 0.528%

content related to sources and references in articles

No Comments

No Known Activations