INDEX

Explanations

terms related to quick summaries and descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

sm

-0.16

 Hell

-0.16

@(

-0.15

 grass

-0.15

/articles

-0.14

 Pearson

-0.14

éŃ

-0.14

 Cond

-0.14

 Maxwell

-0.14

POSITIVE LOGITS

arna

0.16

dfs

0.15

FileSync

0.14

ãĥ¼ãĥĨ

0.14

iets

0.14

Ð¾Ð»Ð¾Ð´

0.14

eldorf

0.14

jb

0.13

ccount

0.13

á»ĩn

0.13

Activations Density 0.000%

terms related to quick summaries and descriptions

No Comments

No Known Activations