INDEX

Explanations

comparisons and evaluations of experiences or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

affen

-0.18

ovny

-0.17

imbus

-0.16

uir

-0.14

rod

-0.14

 persuasion

-0.14

ideo

-0.14

upos

-0.14

odata

-0.13

POSITIVE LOGITS

ega

0.15

iaux

0.15

CHO

0.15

bsp

0.15

.scala

0.15

licht

0.14

.ma

0.14

echa

0.14

ORA

0.14

 COPYRIGHT

0.14

Activations Density 0.404%

comparisons and evaluations of experiences or products

No Comments

No Known Activations