INDEX

Explanations

information related to features and specifications of products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

æ¡Ĥ

-0.14

iy

-0.14

emann

-0.14

åĬª

-0.13

yat

-0.13

ìĪĻ

-0.13

çĲ

-0.13

POSITIVE LOGITS

ooke

0.17

pto

0.17

ãĥªãĥ¼ãĤº

0.16

asename

0.16

elah

0.15

elez

0.15

Hog

0.14

 otherwise

0.14

asel

0.14

ooky

0.14

Activations Density 0.873%

information related to features and specifications of products

No Comments

No Known Activations