INDEX

Explanations

references to software licensing and legal documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ÄĲT

-0.19

urs

-0.16

fi

-0.15

 INTERNAL

-0.15

iders

-0.14

burgh

-0.14

ihan

-0.14

izzo

-0.14

fi

-0.14

OKEN

-0.14

POSITIVE LOGITS

 Hart

0.15

oldt

0.14

achu

0.14

amble

0.13

anst

0.13

emm

0.13

oran

0.13

raÃ§

0.13

 æİ

0.13

 context

0.13

Activations Density 0.004%

references to software licensing and legal documentation

No Comments

No Known Activations