INDEX

Explanations

references to numerical values and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

venes

-0.15

idges

-0.15

zers

-0.15

igo

-0.14

 fitte

-0.14

zens

-0.14

Äĥn

-0.14

ç¨³

-0.13

Ø¯Ø§ÙĨ

-0.13

 ÐºÐ°ÑĪ

-0.13

POSITIVE LOGITS

/single

0.17

lah

0.15

imb

0.15

aver

0.15

affe

0.14

adem

0.14

 giáº£n

0.14

eros

0.14

 simultaneous

0.14

aryl

0.14

Activations Density 0.098%

references to numerical values and specifications

No Comments

No Known Activations