INDEX

Explanations

instances of the letter "W" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

idget

-0.19

allet

-0.17

arrow

-0.17

eb

-0.17

ave

-0.16

heel

-0.15

iki

-0.15

alls

-0.15

ork

-0.15

uges

-0.15

POSITIVE LOGITS

enh

0.15

WISE

0.15

Ð°Ð½ÑĮ

0.14

ictor

0.14

orgen

0.13

ho

0.13

iert

0.13

 simul

0.13

anel

0.13

 pros

0.13

Activations Density 0.039%

instances of the letter "W" in various contexts

No Comments

No Known Activations