INDEX

Explanations

expressions of personal thoughts, beliefs, and assumptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

hma

-0.16

foy

-0.16

ught

-0.15

iek

-0.15

idel

-0.15

akhir

-0.15

adier

-0.14

Ð²ÐµÐ½

-0.14

idden

-0.14

ÛĮØ·

-0.14

POSITIVE LOGITS

 Wass

0.17

ovic

0.17

usi

0.15

ague

0.15

sey

0.15

vise

0.15

 CONTRIBUTORS

0.14

lam

0.14

bach

0.14

se

0.14

Activations Density 0.022%

expressions of personal thoughts, beliefs, and assumptions

No Comments

No Known Activations