INDEX

Explanations

references to specific educational and community-related institutions or concepts

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

à¸¸à¸ķ

-0.16

zug

-0.15

uhl

-0.14

Ð½Ð¾ÑĪ

-0.14

 Mach

-0.14

erno

-0.14

ilyn

-0.14

 Tone

-0.14

Ray

-0.14

 noise

-0.14

POSITIVE LOGITS

AMI

0.15

odic

0.15

avian

0.15

azon

0.14

æĪĲ

0.14

ultz

0.14

orp

0.14

enia

0.14

soles

0.14

_TRNS

0.14

Activations Density 0.150%

references to specific educational and community-related institutions or concepts

No Comments

No Known Activations