INDEX

Explanations

references to individuals and locations, particularly in an academic or professional context

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

uhe

-0.17

andi

-0.15

unce

-0.14

íĻĢ

-0.14

ŀ

-0.14

uhn

-0.14

acz

-0.14

á»Ĳ

-0.14

 Society

-0.13

_tE

-0.13

POSITIVE LOGITS

ãĤ¡

0.15

ëħĦëıĦ

0.14

toi

0.14

Ã§uk

0.13

Ã©v

0.13

forge

0.13

olly

0.13

(exports

0.13

 Blair

0.13

udit

0.13

Activations Density 0.019%

references to individuals and locations, particularly in an academic or professional context

No Comments

No Known Activations