INDEX

Explanations

references to comments within code or documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

iks

-0.15

utin

-0.15

cwd

-0.15

uc

-0.14

Ã¤r

-0.14

EGIN

-0.14

BOOST

-0.14

Lup

-0.13

 stron

-0.13

åł´

-0.13

POSITIVE LOGITS

erson

0.16

ogenic

0.16

gage

0.15

onom

0.15

ace

0.15

hung

0.15

rows

0.15

hana

0.14

Ket

0.14

Ave

0.14

Activations Density 0.020%

references to comments within code or documents

No Comments

No Known Activations