INDEX

Explanations

names of people associated with significant actions or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

appa

-0.16

Î¬Î»Î¹

-0.16

kili

-0.15

rada

-0.15

Ð»ÑıÐ´

-0.15

ekl

-0.15

ê¸ī

-0.14

moth

-0.14

embro

-0.14

imas

-0.14

POSITIVE LOGITS

oney

0.18

0.15

ess

0.15

Ell

0.14

ationToken

0.14

 Halk

0.14

les

0.14

cz

0.14

é¢Ŀ

0.14

Activations Density 0.070%

names of people associated with significant actions or roles

No Comments

No Known Activations