INDEX

Explanations

phrases indicating possession or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

iners

-0.16

hek

-0.16

agar

-0.15

artner

-0.15

aga

-0.14

ãģŀ

-0.14

eniable

-0.14

agger

-0.14

 HttpStatusCode

-0.14

idel

-0.14

POSITIVE LOGITS

UNET

0.16

 certain

0.15

so

0.15

 great

0.15

 young

0.15

Ð½ÐµÐ½Ð¸Ðµ

0.14

 target

0.14

 amazing

0.14

 talented

0.13

fid

0.13

Activations Density 0.129%

phrases indicating possession or relationships

No Comments

No Known Activations