INDEX

Explanations

characters or symbols indicating importance or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 legislative

-0.16

 legis

-0.16

 Legislative

-0.16

 Parliament

-0.16

mpar

-0.15

 lawmakers

-0.15

 Parliamentary

-0.15

 lawmaker

-0.14

æŁ±

-0.14

oya

-0.14

POSITIVE LOGITS

 Clinton

0.27

 Hillary

0.24

Clinton

0.23

 Trump

0.23

 Donald

0.20

Hillary

0.20

 Rubio

0.19

 Clintons

0.19

Trump

0.19

 Sanders

0.19

Activations Density 0.003%

characters or symbols indicating importance or emphasis

No Comments

No Known Activations