INDEX

Explanations

proper nouns, specifically names and locations

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

reta

-0.15

McD

-0.15

 Coloring

-0.15

[top

-0.15

MethodImpl

-0.14

Î¼Î¹

-0.14

 Appeal

-0.14

 Frag

-0.14

appe

-0.14

ardless

-0.13

POSITIVE LOGITS

znik

0.17

ctime

0.14

Î³Î¿Ïį

0.14

amak

0.14

Äįka

0.14

.pageY

0.14

Sector

0.13

sector

0.13

assel

0.13

aviour

0.13

Activations Density 0.000%

proper nouns, specifically names and locations

No Comments

No Known Activations