INDEX

Explanations

structural elements related to web content, particularly in relation to posts and taxonomy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ÑıÐ¶

-0.16

Specifier

-0.15

-ST

-0.15

Ì£

-0.15

ÙĲÙħ

-0.14

arn

-0.14

 round

-0.14

 Chiefs

-0.14

ple

-0.14

MMdd

-0.14

POSITIVE LOGITS

Å¡ek

0.17

ç®±

0.15

 CreateMap

0.15

croll

0.14

 htmlentities

0.14

posts

0.14

/column

0.14

 Rowe

0.14

Ã¶h

0.14

reon

0.14

Activations Density 0.031%

structural elements related to web content, particularly in relation to posts and taxonomy

No Comments

No Known Activations