INDEX

Explanations

formal references to organizations and scientific assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

éŀ

-0.14

 aber

-0.14

 what

-0.13

iers

-0.13

vir

-0.13

XR

-0.13

grim

-0.13

rien

-0.13

aja

-0.13

fol

-0.13

POSITIVE LOGITS

since

0.20

 since

0.19

Since

0.18

 Since

0.18

ä¸ºäºĨ

0.18

During

0.17

 During

0.17

 Beginning

0.17

 Starting

0.16

 during

0.15

Activations Density 0.190%

formal references to organizations and scientific assessments

No Comments

No Known Activations