INDEX

Explanations

technical terminology related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ì´Ī

-0.14

 militar

-0.13

ÎķÎł

-0.12

tol

-0.12

åħ¬åħ±

-0.12

zelf

-0.12

idon

-0.12

[table

-0.12

 Bender

-0.12

POSITIVE LOGITS

 chain

0.14

 Chain

0.13

 Fore

0.13

enn

0.13

ÂĢÂ

0.13

 chains

0.13

ense

0.12

anela

0.12

stem

0.12

fore

0.12

Activations Density 0.435%

technical terminology related to programming and software development

No Comments

No Known Activations