INDEX

Explanations

words related to improvement and self-care

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

okol

-0.19

íĻĶ

-0.17

 åĮĸ

-0.15

olina

-0.15

/AFP

-0.15

ries

-0.15

uth

-0.15

£½

-0.15

kel

-0.15

POSITIVE LOGITS

ILA

0.15

/loader

0.15

 agent

0.15

atory

0.15

hev

0.14

 factor

0.14

agent

0.14

 force

0.14

ative

0.13

urious

0.13

Activations Density 0.299%

words related to improvement and self-care

No Comments

No Known Activations