INDEX

Explanations

information related to historical figures and their contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

occan

-0.16

ushima

-0.15

din

-0.14

//*[

-0.14

 -*-č↵

-0.14

 å¯

-0.14

aktion

-0.13

AppDelegate

-0.13

akan

-0.13

izon

-0.13

POSITIVE LOGITS

ISCO

0.18

 Arcade

0.16

isco

0.15

asco

0.15

inos

0.15

ADOS

0.15

isko

0.14

yer

0.14

ANTE

0.14

 firm

0.14

Activations Density 0.064%

information related to historical figures and their contributions

No Comments

No Known Activations