INDEX

Explanations

references to organized groups and coalitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

avenport

-0.17

èªĮ

-0.16

ungeons

-0.15

.cms

-0.15

elsing

-0.15

sWith

-0.15

addon

-0.15

::*

-0.14

esion

-0.14

variants

-0.14

POSITIVE LOGITS

 gá»ĵm

0.27

of

0.25

 consisting

0.20

 cÃ¡c

0.19

 composed

0.18

ofs

0.17

 nhá»¯ng

0.16

 ÏĦÏīÎ½

0.16

pf

0.16

 halinde

0.16

Activations Density 0.226%

references to organized groups and coalitions

No Comments

No Known Activations