INDEX

Explanations

statements that assert or emphasize a viewpoint or opinion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Ã£i

-0.15

 ucwords

-0.15

ÑĥÑĢÐ°

-0.14

hi

-0.13

TION

-0.13

acman

-0.13

kÃ¼

-0.13

UNDLE

-0.13

uche

-0.13

-:

-0.13

POSITIVE LOGITS

 namely

0.32

nam

0.22

Nam

0.21

 Instead

0.21

 There

0.21

 Each

0.20

It

0.19

 They

0.19

 Either

0.19

viz

0.18

Activations Density 0.083%

statements that assert or emphasize a viewpoint or opinion

No Comments

No Known Activations