INDEX

Explanations

references to historical events and significant figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 foss

-0.17

Browsable

-0.16

statt

-0.15

é£¯

-0.15

iac

-0.14

ÑĥÐ½Ð´

-0.14

 ctor

-0.14

corp

-0.14

rok

-0.14

rod

-0.14

POSITIVE LOGITS

iani

0.15

rror

0.15

SM

0.15

¡

0.15

SM

0.14

mon

0.14

 ÙħÙĦ

0.14

ÙĤÙĩ

0.14

BuilderFactory

0.14

Coverage

0.14

Activations Density 0.289%

references to historical events and significant figures

No Comments

No Known Activations