INDEX

Explanations

phrases related to criticism and comparisons in reviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ã¼m

-0.16

omor

-0.15

Î¬Ïĥ

-0.15

 dÆ°

-0.14

aper

-0.14

 /*#__

-0.13

ãĥ³ãĥĲ

-0.13

rek

-0.13

reff

-0.13

fur

-0.13

POSITIVE LOGITS

pl

0.17

ouble

0.16

poon

0.15

 shame

0.15

HAL

0.14

sea

0.14

Î»Î±

0.14

opup

0.14

instrument

0.14

lash

0.14

Activations Density 0.046%

phrases related to criticism and comparisons in reviews

No Comments

No Known Activations