INDEX

Explanations

prominent references to posters and visual representations in various contexts

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

-0.31

sm

-0.29

sc

-0.29

sel

-0.28

sp

-0.28

sh

-0.28

sWith

-0.28

son

-0.27

sin

-0.26

sid

-0.26

POSITIVE LOGITS

ë§ģ

0.33

er

0.31

idge

0.31

lain

0.30

cury

0.30

gebn

0.28

most

0.27

ocks

0.25

ific

0.25

ization

0.25

Activations Density 0.732%

prominent references to posters and visual representations in various contexts

No Comments

No Known Activations