INDEX

Explanations

nouns and terms related to visual media and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-0.30

sc

-0.27

sm

-0.26

sid

-0.24

sa

-0.24

side

-0.23

sWith

-0.23

sin

-0.23

sh

-0.23

POSITIVE LOGITS

ë§ģ

0.31

idge

0.31

lain

0.27

er

0.26

cury

0.26

gebn

0.25

ocks

0.24

ific

0.24

Ã¸d

0.24

ization

0.24

Activations Density 0.289%

nouns and terms related to visual media and documentation

No Comments

No Known Activations

nouns and terms related to visual media and documentation

No Comments

No Known Activations