INDEX

Explanations

terms related to measurement and categorization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

alley

-0.14

cket

-0.13

amina

-0.13

sing

-0.13

IOD

-0.13

ÄĽtÃŃ

-0.13

alet

-0.13

lox

-0.12

 seperate

-0.12

rooms

-0.12

POSITIVE LOGITS

byss

0.16

ãĥ¼ãĥį

0.15

etheless

0.14

Ð¾Ð¿Ð°Ñģ

0.13

ousse

0.13

.GroupLayout

0.13

istrovstvÃŃ

0.13

atre

0.13

ProgressHUD

0.13

odore

0.13

Activations Density 2.340%

terms related to measurement and categorization

No Comments

No Known Activations