INDEX

Explanations

proper nouns, especially names of people and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ilege

-0.17

 leak

-0.15

ÄŁan

-0.15

à¤¹à¤°

-0.15

queryParams

-0.15

zeit

-0.14

Ð·Ð¸

-0.14

handles

-0.14

 Levy

-0.14

wei

-0.13

POSITIVE LOGITS

Ter

0.19

Ter

0.17

0.16

ter

0.15

TER

0.15

 Cardinal

0.15

peg

0.14

cth

0.14

irma

0.14

cop

0.14

Activations Density 0.026%

proper nouns, especially names of people and places

No Comments

No Known Activations