INDEX

Explanations

proper nouns and names associated with industries, events, or notable individuals

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

neau

-0.14

Enumerable

-0.14

llum

-0.14

ÐºÑĢÐ°

-0.14

mall

-0.13

-wsj

-0.13

ÐĴÑĤ

-0.12

Ã©al

-0.12

CLU

-0.12

 octave

-0.12

POSITIVE LOGITS

Cle

0.14

á»ĳn

0.14

cle

0.14

con

0.14

Lip

0.14

sup

0.14

Sup

0.13

 place

0.13

bon

0.13

bon

0.13

Activations Density 0.637%

proper nouns and names associated with industries, events, or notable individuals

No Comments

No Known Activations