INDEX

Explanations

references to control or dominance in interpersonal or market contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

sville

-0.17

ÑĢÑĥÐ½

-0.15

Alb

-0.15

acc

-0.15

ÑĢÐ°Ñĩ

-0.15

mue

-0.14

mdb

-0.14

QE

-0.14

ä½¿

-0.14

iams

-0.14

POSITIVE LOGITS

 covered

0.38

 Covered

0.34

covered

0.33

-covered

0.24

 figured

0.24

 COVER

0.21

 licked

0.21

peg

0.20

Cover

0.20

 down

0.18

Activations Density 0.095%

references to control or dominance in interpersonal or market contexts

No Comments

No Known Activations