INDEX

Explanations

geographic locations and associated place names

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

à¤¿à¤¹

-0.15

ihar

-0.15

Ð°ÐºÐ¸

-0.15

oui

-0.15

apt

-0.15

 Freund

-0.15

auc

-0.14

gyr

-0.14

upa

-0.14

Ã¡lt

-0.14

POSITIVE LOGITS

0.16

ÙĬØ§

0.16

ÏĦÎ¿Î¼Î±

0.15

POCH

0.15

 sublist

0.15

ê²©

0.14

 oppon

0.14

ahoo

0.14

ainers

0.13

Activations Density 0.049%

geographic locations and associated place names

No Comments

No Known Activations