INDEX

Explanations

questions that express curiosity or seek clarification

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

ay

-0.18

culus

-0.16

.external

-0.16

iferay

-0.15

ypi

-0.15

aba

-0.15

 æ©Ł

-0.15

loff

-0.15

ando

-0.15

est

-0.14

POSITIVE LOGITS

why

0.18

ê³¡

0.15

why

0.15

qid

0.15

unately

0.15

tuz

0.14

 Mentor

0.14

uns

0.14

 rendered

0.14

unting

0.14

Activations Density 0.077%

questions that express curiosity or seek clarification

No Comments

No Known Activations