INDEX

Explanations

references to internal systems and processes within organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ektor

-0.15

WithEmail

-0.14

ä¾¡

-0.14

oning

-0.14

_RETURN

-0.14

ì§ģ

-0.13

ultimate

-0.13

hiro

-0.13

asename

-0.13

NCY

-0.13

POSITIVE LOGITS

most

0.25

halb

0.21

/internal

0.20

/Internal

0.19

ities

0.17

0.16

/embed

0.16

 Affairs

0.16

ise

0.16

ized

0.16

Activations Density 0.032%

references to internal systems and processes within organizations

No Comments

No Known Activations