INDEX

Explanations

variations in character encoding or unusual symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

à¦¾à¦

-0.17

-0.15

Ø¹Ø§Ø¯

-0.15

bdd

-0.15

 pragma

-0.15

eling

-0.14

otp

-0.14

olor

-0.14

æ½®

-0.14

utable

-0.13

POSITIVE LOGITS

lg

0.17

to

0.17

rd

0.16

coma

0.16

yd

0.15

Ø±Øª

0.15

llum

0.15

ctica

0.15

cy

0.15

mill

0.14

Activations Density 0.059%

variations in character encoding or unusual symbols

No Comments

No Known Activations