INDEX

Explanations

references to mainstream culture and media

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

lsen

-0.15

/design

-0.14

ÑĢÐ¾ÑĤ

-0.14

oth

-0.14

xin

-0.14

olle

-0.14

son

-0.14

enti

-0.14

POSITIVE LOGITS

 mainstream

0.19

 dÄ±ÅŁÄ±

0.16

arak

0.16

/Main

0.16

/main

0.16

edList

0.16

izo

0.16

ìłģìľ¼ë¡ľ

0.15

ONGL

0.15

Activations Density 0.014%

references to mainstream culture and media

No Comments

No Known Activations