INDEX

Explanations

phrases indicating availability or access to information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Allowed

-0.14

.Serialize

-0.14

eti

-0.14

Ð»ÐµÐ²

-0.13

););↵

-0.13

richt

-0.13

_allowed

-0.13

.nz

-0.13

tÃ©

-0.12

ĻĤ

-0.12

POSITIVE LOGITS

 found

0.43

found

0.37

 Found

0.35

 FOUND

0.33

-found

0.32

Found

0.31

 viewed

0.31

_found

0.30

(found

0.28

 seen

0.27

Activations Density 0.038%

phrases indicating availability or access to information

No Comments

No Known Activations