INDEX

Explanations

phrases that contain questions about definitions and explanations of concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ehler

-0.15

empl

-0.15

UBL

-0.15

UCH

-0.14

ift

-0.14

ansen

-0.14

ebo

-0.14

ily

-0.14

_TLS

-0.14

immel

-0.14

POSITIVE LOGITS

ĵåĲį

0.15

enza

0.14

warz

0.14

adlo

0.14

pio

0.13

 Daniels

0.13

ÃŃsto

0.13

à¤¹à¤¨

0.13

.opens

0.13

 Scre

0.13

Activations Density 0.073%

phrases that contain questions about definitions and explanations of concepts

No Comments

No Known Activations