INDEX

Explanations

references to reviews or summaries of content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

yps

-0.16

uno

-0.15

uckles

-0.14

adar

-0.14

ANO

-0.13

cts

-0.13

rung

-0.13

udson

-0.13

 KÃ¼r

-0.13

ÐµÐ½Ð¸Ð¹

-0.13

POSITIVE LOGITS

ers

0.21

itler

0.19

azo

0.16

istrovstvÃŃ

0.16

er

0.15

 aggregation

0.15

.Expressions

0.15

erb

0.14

nett

0.14

èĩªæĭį

0.14

Activations Density 0.018%

references to reviews or summaries of content

No Comments

No Known Activations