INDEX

Explanations

terms related to defense or definitions of defense

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

¶Į

-0.16

frau

-0.16

frei

-0.15

hev

-0.15

kke

-0.15

blick

-0.15

INGLE

-0.15

velt

-0.14

éļĨ

-0.14

fabs

-0.14

POSITIVE LOGITS

eat

0.38

eated

0.37

inite

0.35

initely

0.35

init

0.35

eating

0.35

ective

0.34

ining

0.33

ending

0.32

enders

0.31

Activations Density 0.015%

terms related to defense or definitions of defense

No Comments

No Known Activations