INDEX

Explanations

references to "Friends" and related entities or concepts in a community context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 chances

-0.16

	union

-0.15

vey

-0.15

chl

-0.15

rez

-0.14

 Ã¶l

-0.14

 chim

-0.14

 glam

-0.14

 whom

-0.14

ovo

-0.14

POSITIVE LOGITS

LY

0.17

ply

0.17

ENTA

0.16

ukan

0.16

lies

0.16

asca

0.15

amac

0.15

liness

0.15

aeda

0.15

lier

0.15

Activations Density 0.010%

references to "Friends" and related entities or concepts in a community context

No Comments

No Known Activations