INDEX

Explanations

phrases indicating the existence of research findings or evidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 elucid

-0.17

fen

-0.15

avir

-0.14

ody

-0.14

 Recap

-0.14

è¢ĸ

-0.14

orna

-0.14

wz

-0.14

omal

-0.14

ONA

-0.14

POSITIVE LOGITS

 shown

0.43

shown

0.34

 show

0.33

-show

0.28

 demonstrated

0.27

 showed

0.26

Shown

0.26

show

0.25

 shows

0.24

 Show

0.24

Activations Density 0.077%

phrases indicating the existence of research findings or evidence

No Comments

No Known Activations