INDEX

Explanations

the word "another."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

_consts

-0.15

/dat

-0.15

gren

-0.15

pedia

-0.15

adan

-0.15

 olmayan

-0.14

 serialVersionUID

-0.14

ponent

-0.14

 parental

-0.14

 ç³

-0.14

POSITIVE LOGITS

 Peyton

0.16

.ga

0.15

ness

0.14

iros

0.14

el

0.14

los

0.14

isine

0.14

utzer

0.13

DOI

0.13

arya

0.13

Activations Density 0.031%

the word "another."

No Comments

No Known Activations