INDEX

Explanations

variations of the word "question" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

shire

-0.18

reu

-0.15

.tell

-0.14

 Prairie

-0.14

-ul

-0.14

gow

-0.14

igkeit

-0.14

/fixtures

-0.14

PIO

-0.14

ìį¨

-0.14

POSITIVE LOGITS

naires

0.25

naire

0.23

stell

0.18

pare

0.16

stown

0.15

blade

0.15

nal

0.15

odÃŃ

0.15

yntax

0.14

lycer

0.14

Activations Density 0.044%

variations of the word "question" in different contexts

No Comments

No Known Activations