INDEX

Explanations

words related to giving hints or suggestions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

iske

-0.17

anten

-0.16

ourg

-0.16

Ã¡zÃŃ

-0.14

 Noir

-0.14

airie

-0.14

acic

-0.14

ÅĻeh

-0.13

aeda

-0.13

ilver

-0.13

POSITIVE LOGITS

ings

0.16

INGS

0.15

æĺŃåĴĮ

0.15

 atom

0.15

fa

0.14

 Morm

0.14

dash

0.14

 absor

0.14

iated

0.14

Cav

0.13

Activations Density 0.012%

words related to giving hints or suggestions

No Comments

No Known Activations

words related to giving hints or suggestions

No Comments

No Known Activations