INDEX

Explanations

instances of accountability and assurance in contexts of criticism or controversy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

elon

-0.19

tua

-0.15

loh

-0.15

ilver

-0.14

clud

-0.14

Ø§Ø³ÙĬ

-0.14

Bud

-0.14

lland

-0.14

ald

-0.14

ussen

-0.14

POSITIVE LOGITS

us

0.30

him

0.23

me

0.17

 nhau

0.17

avic

0.15

 ÐµÐ¼Ñĥ

0.15

 anyone

0.15

 them

0.15

 anybody

0.15

ulse

0.15

Activations Density 0.716%

instances of accountability and assurance in contexts of criticism or controversy

No Comments

No Known Activations