INDEX

Explanations

information about protagonists facing dangerous situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

oux

-0.18

rega

-0.16

aler

-0.16

urtle

-0.15

vant

-0.15

 æĿ¾

-0.15

reau

-0.15

astr

-0.14

ater

-0.14

HITE

-0.14

POSITIVE LOGITS

 Central

0.17

ÃŃd

0.16

 Kelly

0.15

 contract

0.15

ags

0.15

ebi

0.14

 Fund

0.14

 Esper

0.14

oni

0.14

 fund

0.14

Activations Density 0.183%

information about protagonists facing dangerous situations

No Comments

No Known Activations