INDEX

Explanations

discussions about film and entertainment, particularly those that involve critical evaluations and reviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

æĹ

-0.15

ãĥ¼ãĤ¹

-0.15

á»©c

-0.14

ichi

-0.14

izzie

-0.14

irie

-0.14

 Ð¸Ð¼Ñĥ

-0.14

èģŀ

-0.14

rese

-0.13

Î»ÏĮÎ³

-0.13

POSITIVE LOGITS

 saying

0.65

 stating

0.44

 remark

0.37

 noting

0.36

 calling

0.35

 Saying

0.35

say

0.31

 claiming

0.30

claim

0.29

SAY

0.29

Activations Density 0.714%

discussions about film and entertainment, particularly those that involve critical evaluations and reviews

No Comments

No Known Activations