INDEX

Explanations

geographical locations and addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

rix

-0.19

ÙĪÙħØ§Øª

-0.16

lick

-0.15

perator

-0.15

PasswordEncoder

-0.14

nces

-0.14

perm

-0.14

)sender

-0.14

_userdata

-0.14

illard

-0.14

POSITIVE LOGITS

osa

0.19

 Rochester

0.18

 Byron

0.17

0.16

Far

0.16

 Chat

0.15

ç´

0.15

iche

0.15

 Dover

0.14

ichi

0.14

Activations Density 0.010%

geographical locations and addresses

No Comments

No Known Activations