INDEX

Explanations

references to individuals, particularly in the context of obituaries or memorials

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

ungan

-0.17

bourne

-0.16

aln

-0.15

afi

-0.14

 acts

-0.14

Å¡em

-0.14

onders

-0.14

ä¸įè¶³

-0.14

eturn

-0.14

agal

-0.14

POSITIVE LOGITS

 leaves

0.40

 Leaves

0.35

 touched

0.25

 leaf

0.24

Leaf

0.24

 Leaf

0.24

 leave

0.24

 touch

0.23

leaf

0.22

èĳī

0.22

Activations Density 0.031%

references to individuals, particularly in the context of obituaries or memorials

No Comments

No Known Activations