INDEX

Explanations

references to publications and literary works

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

rowing

-0.15

uisse

-0.15

atab

-0.15

ä»ĭ

-0.14

oreach

-0.14

 rematch

-0.14

ick

-0.13

odu

-0.13

-io

-0.13

dk

-0.13

POSITIVE LOGITS

enza

0.15

Suc

0.14

DEF

0.14

imenti

0.14

 consort

0.14

conexion

0.14

 conv

0.13

AGING

0.13

ordion

0.13

Putin

0.13

Activations Density 0.088%

references to publications and literary works

No Comments

No Known Activations