INDEX

Explanations

variations of the word "look"

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

ials

-0.18

inea

-0.16

agon

-0.16

Ã©ment

-0.16

imdi

-0.15

MENT

-0.15

eka

-0.14

borg

-0.14

ive

-0.14

innen

-0.14

POSITIVE LOGITS

outs

0.20

UpEdit

0.19

AndFeel

0.18

ups

0.18

ÂŃing

0.17

 alike

0.16

adoo

0.16

å¾ħ

0.15

ingly

0.15

LIK

0.15

Activations Density 0.088%

variations of the word "look"

No Comments

No Known Activations