INDEX

Explanations

references to people and their social interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ãģĦãĤĭ

-0.22

ãģĦãģŁ

-0.21

ample

-0.15

————————

-0.15

à¸Ļ

-0.15

ãĤ©

-0.15

 sayÄ±da

-0.14

endar

-0.14

izi

-0.14

stu

-0.14

POSITIVE LOGITS

à¸£

0.20

ering

0.17

ÙħØ§ÙĦ

0.17

tuk

0.16

prav

0.15

acon

0.15

ment

0.15

uter

0.15

à¤¨

0.15

Activations Density 0.181%

references to people and their social interactions

No Comments

No Known Activations