INDEX

Explanations

references to political decisions and their consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ctp

-0.16

 Tube

-0.14

zung

-0.14

amera

-0.14

adius

-0.13

èĴ

-0.13

 tube

-0.13

 tubes

-0.13

.cg

-0.13

xad

-0.13

POSITIVE LOGITS

RSS

0.34

 Hind

0.32

rss

0.27

RSS

0.25

 communal

0.24

AIM

0.24

Ram

0.23

 Hindus

0.23

/rss

0.23

 hind

0.23

Activations Density 0.068%

references to political decisions and their consequences

No Comments

No Known Activations