INDEX

Explanations

references to academic citations or research papers

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

cripts

-0.16

Cla

-0.14

colo

-0.14

inet

-0.14

Nano

-0.14

gorm

-0.14

INET

-0.13

Ïį

-0.13

Å¡ak

-0.13

aget

-0.13

POSITIVE LOGITS

/cs

0.14

ocha

0.13

 Ã¡n

0.13

ÑħÐ¾

0.13

 Georgetown

0.13

Ł

0.13

 Courtesy

0.13

iazza

0.13

ÐµÑĢÐ°Ð»ÑĮ

0.13

Activations Density 0.002%

references to academic citations or research papers

No Comments

No Known Activations