INDEX

Explanations

instances of interviews and related formats

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

anson

-0.17

ÐµÐ´Ð¸Ð½Ð¸

-0.15

Sug

-0.15

esen

-0.15

onda

-0.15

 ((__

-0.14

 porad

-0.13

 è«

-0.13

gan

-0.13

ottes

-0.13

POSITIVE LOGITS

0.17

icode

0.15

0.14

 interviews

0.14

olem

0.14

Ã¼stÃ¼

0.14

 LENG

0.14

ingleton

0.14

åıĸ

0.14

Activations Density 0.030%

instances of interviews and related formats

No Comments

No Known Activations