INDEX

Explanations

references to categorization, evaluation, or classification of concepts or individuals

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

 Wald

-0.16

.pivot

-0.15

ØŃØ¯

-0.15

olg

-0.15

Ã¶g

-0.14

ÑģÐ¸Ð¼

-0.14

plements

-0.14

ILD

-0.14

 distributed

-0.13

 dziew

-0.13

POSITIVE LOGITS

 pile

0.21

 list

0.21

 bucket

0.20

ategori

0.19

 camp

0.19

bucket

0.18

pile

0.17

amarin

0.17

 category

0.17

ibox

0.17

Activations Density 0.139%

references to categorization, evaluation, or classification of concepts or individuals

No Comments

No Known Activations