INDEX

Explanations

words and phrases associated with political and social issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

able

-0.18

ables

-0.17

ORB

-0.17

erez

-0.17

ive

-0.16

IRD

-0.15

ird

-0.15

ified

-0.14

edula

-0.14

(er

-0.14

POSITIVE LOGITS

 speaking

0.28

 sound

0.27

sound

0.25

 Speaking

0.24

 minded

0.23

 SOUND

0.22

Speaking

0.21

 Sound

0.21

Sound

0.21

/math

0.21

Activations Density 0.062%

words and phrases associated with political and social issues

No Comments

No Known Activations

words and phrases associated with political and social issues

No Comments

No Known Activations