INDEX

Explanations

names of people prominent in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 himself

-0.17

Woo

-0.15

uss

-0.14

Erf

-0.14

son

-0.14

Lev

-0.14

 Baxter

-0.14

ÑĥÑģ

-0.14

 Levin

-0.14

POSITIVE LOGITS

 herself

0.20

ovÃ¡

0.16

]=="

0.15

jeme

0.15

 lesbian

0.15

ovna

0.15

 Lesbian

0.15

fone

0.15

ÙĬØ¯Ø©

0.15

},'

0.15

Activations Density 0.080%

names of people prominent in various contexts

No Comments

No Known Activations