INDEX

Explanations

references to the concept of "belonging" or "community."

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

es

-0.31

ed

-0.27

ey

-0.24

ep

-0.24

em

-0.24

essa

-0.23

ez

-0.23

ella

-0.23

ectomy

-0.23

ese

-0.22

POSITIVE LOGITS

er

0.27

hythm

0.25

ough

0.23

ashtra

0.22

tesy

0.21

riculum

0.21

iginal

0.21

Ã¸d

0.20

hyth

0.19

erule

0.19

Activations Density 0.060%

references to the concept of "belonging" or "community."

No Comments

No Known Activations