INDEX

Explanations

words related to recommendations and reviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

igkeit

-0.17

ÏģÎµÎ¹

-0.15

ungen

-0.15

 Hansen

-0.14

 stand

-0.14

ings

-0.14

ers

-0.14

]("

-0.14

squeeze

-0.14

est

-0.14

POSITIVE LOGITS

bourg

0.16

åĴ²

0.15

-described

0.15

elez

0.15

thag

0.14

 descri

0.14

acional

0.14

agr

0.14

pace

0.14

ya

0.14

Activations Density 0.011%

words related to recommendations and reviews

No Comments

No Known Activations