INDEX

Explanations

references to violence 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 @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

nga

-0.18

maze

-0.16

lation

-0.15

edy

-0.15

ilter

-0.15

rid

-0.15

roit

-0.15

edar

-0.15

èĸĦ

-0.15

åĪĩãĤĬ

-0.15

POSITIVE LOGITS

 Against

0.18

ometown

0.17

0.16

eon

0.15

 against

0.15

uous

0.15

ive

0.15

ante

0.15

 committed

0.14

 Dove

0.14

Activations Density 0.025%

references to violence in various contexts

No Comments

No Known Activations