INDEX

Explanations

actions involving violence or physical confrontation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ends

-0.16

needle

-0.16

 Minds

-0.15

ãĥ¼ãĥĹ

-0.15

endid

-0.14

_unpack

-0.14

inky

-0.14

oric

-0.14

dle

-0.14

 Spoon

-0.14

POSITIVE LOGITS

 hard

0.33

 square

0.31

 HARD

0.27

hard

0.27

 harder

0.25

 Hard

0.23

 Square

0.23

Hard

0.21

-hard

0.21

-square

0.20

Activations Density 0.051%

actions involving violence or physical confrontation

No Comments

No Known Activations