INDEX

Explanations

references to specific years or time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ÑĶÐ¼

-0.17

yro

-0.16

Ctrls

-0.14

DevExpress

-0.14

è¼

-0.14

itmap

-0.14

lettes

-0.14

 Ð¿ÐµÑĢÐ¸

-0.14

 Moff

-0.14

ties

-0.13

POSITIVE LOGITS

 siguiente

0.17

achten

0.16

 following

0.14

xia

0.14

ogy

0.14

å¼ı

0.14

imir

0.14

 pocket

0.14

Ø´Ùħ

0.14

Activations Density 0.028%

references to specific years or time periods

No Comments

No Known Activations