INDEX

Explanations

phrases indicating support and assistance in various contexts

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

clud

-0.15

Respons

-0.15

cob

-0.15

 Respons

-0.15

,retain

-0.15

AllowAnonymous

-0.14

æĸ

-0.14

ural

-0.14

 Stevenson

-0.14

ascii

-0.14

POSITIVE LOGITS

aras

0.18

anio

0.16

UPPORT

0.16

/support

0.15

ALSE

0.15

æµ¦

0.15

ESC

0.15

 Crest

0.14

jav

0.14

_FALL

0.14

Activations Density 0.084%

phrases indicating support and assistance in various contexts

No Comments

No Known Activations