INDEX

Explanations

conjunctions and contrasting phrases

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 trous

-0.17

Ì

-0.17

_readable

-0.15

esson

-0.14

_IMPORTED

-0.14

Difference

-0.14

rase

-0.13

emd

-0.13

rgan

-0.13

Zub

-0.13

POSITIVE LOGITS

ablo

0.14

 bucks

0.14

Å¡ak

0.14

ÑĥÐ»Ð¸

0.14

 hope

0.14

 Esper

0.14

æĬľ

0.14

Å¡ek

0.13

ollywood

0.13

ollo

0.13

Activations Density 0.170%

conjunctions and contrasting phrases

No Comments

No Known Activations