INDEX

Explanations

conversational phrases and expressions indicating agreement or concession

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

 Replies

-0.17

å¥´

-0.15

à¸µà¹ī

-0.15

azu

-0.14

egra

-0.13

amaz

-0.13

fÃ©

-0.13

zan

-0.13

astle

-0.13

oms

-0.12

POSITIVE LOGITS

kip

0.16

iversit

0.15

htub

0.15

ãĤ·ãĤ¢

0.15

_lineno

0.15

ouser

0.14

 redund

0.14

 bufsize

0.14

 McGu

0.14

roscope

0.13

Activations Density 0.136%

conversational phrases and expressions indicating agreement or concession

No Comments

No Known Activations