INDEX

Explanations

references to specific locations or landmarks

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

esti

-0.17

elu

-0.16

estar

-0.16

ullan

-0.15

ullivan

-0.15

ideographic

-0.15

icap

-0.15

Ð°Ð»Ð¾Ð²

-0.14

çģ

-0.14

ault

-0.14

POSITIVE LOGITS

ted

0.21

anches

0.17

sets

0.17

rees

0.16

tes

0.16

-nil

0.16

xed

0.15

uations

0.15

rient

0.15

á»¹

0.15

Activations Density 0.042%

references to specific locations or landmarks

No Comments

No Known Activations