INDEX

Explanations

terms related to processes and methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

)NULL

-0.14

 speaks

-0.13

è¡¨ç¤º

-0.12

 ÑĥÐºÐ°Ð·

-0.12

gems

-0.12

vida

-0.12

 Indicates

-0.12

edd

-0.12

lamaz

-0.12

ÑĤÐ°Ð¶

-0.11

POSITIVE LOGITS

 involve

0.47

 involves

0.46

 consist

0.45

 consists

0.42

 involved

0.42

 consisted

0.40

 entail

0.36

 entails

0.35

 involving

0.32

cons

0.31

Activations Density 0.300%

terms related to processes and methods

No Comments

No Known Activations