INDEX

Explanations

words related to visual perception or examining situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

imity

-0.16

avra

-0.16

ddy

-0.16

upert

-0.15

 DÃŃky

-0.15

lek

-0.15

ÙĤØ§Ùħ

-0.15

ahoo

-0.14

coma

-0.14

utures

-0.14

POSITIVE LOGITS

hol

0.27

 beyond

0.26

 past

0.24

 toward

0.20

af

0.20

 favor

0.19

 ways

0.19

 ahead

0.19

Hol

0.19

 seriously

0.19

Activations Density 0.032%

words related to visual perception or examining situations

No Comments

No Known Activations