INDEX

Explanations

references to different elements or components in various contexts

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

dy

-0.18

ska

-0.17

sz

-0.16

nze

-0.14

flt

-0.14

Ã¼Ã§

-0.14

nik

-0.14

Duy

-0.13

 contrary

-0.13

POSITIVE LOGITS

pects

0.18

aspect

0.17

 aspect

0.17

 aspects

0.17

alan

0.14

tra

0.14

æĸ¹éĿ¢

0.14

è±Ĭ

0.14

atoi

0.14

olic

0.14

Activations Density 0.024%

references to different elements or components in various contexts

No Comments

No Known Activations