INDEX

Explanations

terminology and phrases related to violence and brutality

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

 grav

-0.16

lder

-0.15

ationship

-0.15

Unsafe

-0.15

à¤Ĥà¤¶

-0.14

_EMIT

-0.14

orris

-0.14

grav

-0.14

éĽ²

-0.14

abel

-0.13

POSITIVE LOGITS

 treatment

0.23

lest

0.21

ly

0.21

 Treatment

0.20

vard

0.20

ness

0.18

-force

0.17

 honesty

0.17

rone

0.16

PEND

0.16

Activations Density 0.072%

terminology and phrases related to violence and brutality

No Comments

No Known Activations