INDEX

Explanations

specific nouns and proper nouns within the text

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 unins

-0.16

idor

-0.16

omon

-0.15

ledge

-0.13

vÄĽ

-0.13

aucoup

-0.13

idot

-0.12

 Belle

-0.12

ï¼ļ↵

-0.12

POSITIVE LOGITS

/AFP

0.14

/**<

0.14

 svens

0.14

ernel

0.14

esan

0.14

labs

0.13

iropr

0.13

ysa

0.13

rack

0.13

Fcn

0.13

Activations Density 0.204%

specific nouns and proper nouns within the text

No Known Activations