INDEX

Explanations

words indicating potential customers or users in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ëĭ´

-0.16

swire

-0.16

ÐĲÑĢÑħÑĸÐ²

-0.15

zte

-0.15

ynÄ±

-0.15

ogra

-0.15

leck

-0.15

EXPR

-0.14

auga

-0.14

rire

-0.14

POSITIVE LOGITS

 want

0.32

who

0.30

 wanting

0.29

want

0.29

 looking

0.29

 seeking

0.29

seek

0.27

 wants

0.25

 interested

0.25

 Want

0.25

Activations Density 0.147%

words indicating potential customers or users in various contexts

No Comments

No Known Activations