INDEX

Explanations

concepts related to decision-making, comparison, and conditions for acceptability

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

ä¸ĢåĪĩ

-0.15

äºĽ

-0.13

ÏģÎ¿

-0.12

outil

-0.12

 sexle

-0.12

 ragaz

-0.11

 Prostitutas

-0.11

 wszyst

-0.11

NullOr

-0.11

oleÄį

-0.11

POSITIVE LOGITS

0.93

an

0.71

0.48

0.46

ä¸Ģä¸ª

0.44

,a

0.43

)a

0.39

_a

0.39

ä¸ĢåĢĭ

0.36

 another

0.35

Activations Density 6.982%

concepts related to decision-making, comparison, and conditions for acceptability

No Comments

No Known Activations