INDEX

Explanations

phrases indicating responsibility and accountability 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 @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ERO

-0.15

åĥį

-0.14

sek

-0.14

las

-0.14

ViewItem

-0.14

anon

-0.14

gow

-0.14

arel

-0.14

tron

-0.14

Ã¼Ã§

-0.13

POSITIVE LOGITS

IGHL

0.17

 Barton

0.16

Cab

0.16

.scalablytyped

0.16

 everything

0.15

alsa

0.15

zia

0.14

 cost

0.14

forth

0.14

nock

0.14

Activations Density 0.044%

phrases indicating responsibility and accountability in various contexts

No Comments

No Known Activations