INDEX

Explanations

references to magazines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

most

-0.15

ients

-0.15

fer

-0.15

ano

-0.14

alk

-0.14

oko

-0.14

shr

-0.14

imer

-0.14

 conv

-0.14

 Rita

-0.13

POSITIVE LOGITS

esium

0.19

ulumi

0.18

eken

0.17

yntax

0.15

_THAT

0.15

noop

0.15

_exports

0.15

gesi

0.14

artner

0.14

SSION

0.14

Activations Density 0.013%

references to magazines

No Comments

No Known Activations