INDEX

Explanations

references to specific file formats and data types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

icha

-0.18

roman

-0.15

ç²Ĺ

-0.14

 Prem

-0.14

Hue

-0.14

-0.13

.tpl

-0.13

Ful

-0.13

Codes

-0.13

POSITIVE LOGITS

 formats

0.18

jvu

0.18

 opened

0.17

opening

0.17

æł¼å¼ı

0.17

formats

0.17

 format

0.16

æīĵå¼Ģ

0.16

affen

0.16

 opening

0.16

Activations Density 0.120%

references to specific file formats and data types

No Comments

No Known Activations