INDEX

Explanations

comparative phrases indicating quality or similarity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ho

-0.18

ha

-0.15

ant

-0.14

 Editors

-0.14

Â©

-0.14

 Leer

-0.14

-0.13

ÏĦÏĥ

-0.13

 ander

-0.13

ingo

-0.13

POSITIVE LOGITS

 than

0.19

-than

0.18

 THAN

0.16

Than

0.15

Ú©Ùĩ

0.15

ulary

0.15

ThanOrEqualTo

0.14

than

0.14

ething

0.14

_than

0.14

Activations Density 0.010%

comparative phrases indicating quality or similarity

No Comments

No Known Activations