INDEX

Explanations

phrases about review ratings and feedback on video games

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

atis

-0.16

ãĥ©ãĤ¹

-0.15

naz

-0.15

plode

-0.14

inas

-0.14

 Heck

-0.14

ä¸īçº§

-0.14

mime

-0.14

last

-0.14

reate

-0.14

POSITIVE LOGITS

_reviews

0.16

 reviews

0.16

ibox

0.15

 Clover

0.15

 Collider

0.15

 agreg

0.15

 collider

0.15

Collider

0.15

-rating

0.15

 Reviews

0.14

Activations Density 0.056%

phrases about review ratings and feedback on video games

No Comments

No Known Activations