INDEX

Explanations

instances of the word "on" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ability

-0.15

ref

-0.15

eldorf

-0.14

Ã«l

-0.14

objs

-0.14

íĴĪ

-0.14

ksi

-0.14

.microsoft

-0.14

POSITIVE LOGITS

è¼ī

0.16

seau

0.15

eyed

0.14

cce

0.14

 prescription

0.14

uet

0.13

å¼ĢæĶ¾

0.13

 Hole

0.13

 ster

0.13

 Hakk

0.12

Activations Density 0.003%

instances of the word "on" in various contexts

No Comments

No Known Activations