INDEX

Explanations

terms related to business regulations and political discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

(s

-0.23

(es

-0.20

 itself

-0.20

Ñķ

-0.19

’s

-0.19

fulness

-0.18

ssize

-0.17

's

-0.17

iverz

-0.17

serve

-0.16

POSITIVE LOGITS

heets

0.34

cape

0.34

ides

0.28

cales

0.27

 themselves

0.26

’

0.26

ickness

0.24

linger

0.24

uits

0.23

Activations Density 3.151%

terms related to business regulations and political discussions

No Comments

No Known Activations