INDEX

Explanations

proper nouns, particularly names of individuals and brands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ouz

-0.15

ÎºÎ»Î·

-0.15

inand

-0.15

ContentAlignment

-0.15

alse

-0.15

ast

-0.15

aque

-0.14

lator

-0.14

uxe

-0.14

tÃŃ

-0.14

POSITIVE LOGITS

urret

0.15

fuse

0.13

 Studio

0.13

ãĢģãĢģ

0.13

igh

0.13

åİĨ

0.13

 Projectile

0.13

idos

0.13

 ratings

0.13

 Secret

0.12

Activations Density 0.080%

proper nouns, particularly names of individuals and brands

No Comments

No Known Activations