INDEX

Explanations

references to space missions and disasters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Emitter

-0.16

ivant

-0.15

odie

-0.14

ì¶ķ

-0.14

JNI

-0.14

 Eisen

-0.14

LEGRO

-0.14

gressor

-0.14

 Tavern

-0.14

Club

-0.14

POSITIVE LOGITS

ST

0.33

STS

0.31

 Columbia

0.30

 shuttle

0.28

 Discovery

0.27

 Shuttle

0.27

sts

0.27

 Atlantis

0.26

-ST

0.24

 Ende

0.24

Activations Density 0.007%

references to space missions and disasters

No Comments

No Known Activations