INDEX

Explanations

key terms related to characters and significant moments in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

elm

-0.16

Oak

-0.16

VX

-0.15

Oak

-0.15

Buf

-0.14

 ASIC

-0.14

Caj

-0.14

cole

-0.14

 Fuse

-0.14

Registry

-0.14

POSITIVE LOGITS

 Wonder

0.48

 Diana

0.43

Wonder

0.40

 Amazon

0.32

DC

0.31

WW

0.30

Gal

0.28

Gad

0.28

 wonder

0.28

 Them

0.28

Activations Density 0.010%

key terms related to characters and significant moments in narratives

No Comments

No Known Activations