INDEX

Explanations

references to software bugs and issues

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Bronze

-0.17

ãĤ»ãĥ³

-0.15

olt

-0.15

OLT

-0.15

Ø±Ø¨ÛĮ

-0.14

 ìĦ¼

-0.14

ija

-0.14

ild

-0.14

uries

-0.13

 Held

-0.13

POSITIVE LOGITS

gress

0.16

lion

0.15

zilla

0.15

unnel

0.14

ã

0.14

iface

0.13

Fav

0.13

killer

0.13

 funnel

0.13

 Dhabi

0.13

Activations Density 0.022%

references to software bugs and issues

No Known Activations