INDEX

Explanations

phrases related to challenges and achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

claimer

-0.14

 ÎºÎ¿Ïħ

-0.14

hart

-0.14

exampleModal

-0.13

mlink

-0.13

 ÏĩÏī

-0.13

Ð¾ÑĢÐ°Ð·

-0.13

baugh

-0.13

missive

-0.13

RR

-0.13

POSITIVE LOGITS

 done

0.18

 Ð´ÐµÐ»Ð¾

0.17

.scalablytyped

0.16

 task

0.16

-done

0.15

 Done

0.14

 Pill

0.14

ambia

0.14

isco

0.14

done

0.14

Activations Density 0.338%

phrases related to challenges and achievements

No Comments

No Known Activations