INDEX

Explanations

questions and statements indicating definitions or inquiries about existence and characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

iese

-0.15

uler

-0.15

 elsewhere

-0.14

lo

-0.14

.epam

-0.14

 Germ

-0.14

 example

-0.13

 Bair

-0.13

cr

-0.13

wap

-0.13

POSITIVE LOGITS

obl

0.16

asz

0.15

anges

0.15

.PropertyType

0.15

angs

0.14

 serum

0.14

Ð¾Ð¶

0.14

rends

0.14

timing

0.14

utow

0.13

Activations Density 0.013%

questions and statements indicating definitions or inquiries about existence and characteristics

No Comments

No Known Activations