INDEX

Explanations

specific names or brands related to products and individuals

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ugin

-0.15

à¤¬à¤²

-0.14

Æ°á»Ľ

-0.14

/boot

-0.14

 indir

-0.13

rian

-0.13

 sana

-0.13

oredProcedure

-0.13

ï¿¥

-0.13

ocator

-0.13

POSITIVE LOGITS

hin

0.16

UTF

0.16

ies

0.15

Lon

0.14

 Klein

0.14

åĲ¾

0.14

ilos

0.14

 Glam

0.14

 WHATSOEVER

0.14

 Prem

0.14

Activations Density 0.220%

specific names or brands related to products and individuals

No Comments

No Known Activations