INDEX

Explanations

mentions of "Walt" or "Walt Disney."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

er

-0.20

ho

-0.19

eru

-0.18

erus

-0.18

hoff

-0.17

hos

-0.17

oop

-0.16

hq

-0.16

eri

-0.16

hood

-0.16

POSITIVE LOGITS

itudes

0.22

 Disney

0.21

azor

0.20

zheimer

0.17

ãĥīãĥ«

0.17

zman

0.16

uristic

0.16

vos

0.16

zes

0.15

imized

0.15

Activations Density 0.009%

mentions of "Walt" or "Walt Disney."

No Comments

No Known Activations