INDEX

Explanations

instances of tagging or categorization within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Hell

-0.17

 Bureau

-0.15

FromClass

-0.15

Ð°Ð»ÑĮÐ½Ðµ

-0.14

camp

-0.14

ayi

-0.14

.presenter

-0.14

arc

-0.14

ãĥ³ãĥĶ

-0.13

 Bust

-0.13

POSITIVE LOGITS

ged

0.20

steen

0.16

Net

0.15

 çİ©

0.14

cka

0.14

afil

0.14

mith

0.14

ksen

0.13

sten

0.13

Activations Density 0.006%

instances of tagging or categorization within the text

No Comments

No Known Activations