INDEX

Explanations

phrases indicating historical significance or notable events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

icz

-0.18

-0.17

eya

-0.15

lev

-0.15

iegel

-0.15

duk

-0.15

è®°

-0.14

visa

-0.14

auen

-0.14

enson

-0.14

POSITIVE LOGITS

dana

0.15

baum

0.14

ices

0.14

å®ħ

0.14

ance

0.14

toi

0.13

_SAFE

0.13

 nested

0.13

BS

0.13

steen

0.13

Activations Density 0.163%

phrases indicating historical significance or notable events

No Comments

No Known Activations