INDEX

Explanations

references to specific products or technology developments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

stvÃŃ

-0.15

irit

-0.15

asso

-0.15

aversable

-0.15

arend

-0.15

oplevel

-0.14

ocz

-0.14

ê¸ī

-0.13

Kit

-0.13

POSITIVE LOGITS

odel

0.21

burgh

0.16

omed

0.15

gate

0.15

éĢĲ

0.15

á»ĳi

0.14

 HÃ¼s

0.14

agos

0.13

 Schmidt

0.13

Ã¤d

0.13

Activations Density 1.239%

references to specific products or technology developments

No Comments

No Known Activations