INDEX

Explanations

references to actors and their performances

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

ynom

-0.16

engo

-0.15

.cg

-0.15

erse

-0.15

semb

-0.15

(TM

-0.14

visions

-0.14

.xz

-0.14

-0.13

sÃŃ

-0.13

POSITIVE LOGITS

 Starr

0.23

st

0.22

 essays

0.21

-st

0.20

 opposite

0.20

rop

0.20

 essay

0.20

gro

0.19

 groove

0.19

 Katrina

0.19

Activations Density 0.018%

references to actors and their performances

No Comments

No Known Activations