INDEX

Explanations

references to written works and publications

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

ê°¤

-0.15

angers

-0.15

oders

-0.13

ippers

-0.13

encers

-0.13

nels

-0.13

agers

-0.13

holes

-0.13

and

-0.13

-offs

-0.13

POSITIVE LOGITS

isode

0.22

ogram

0.19

ulet

0.18

Ø®Ø©

0.17

ologue

0.17

slaught

0.16

ISODE

0.16

otype

0.16

athon

0.16

orama

0.16

Activations Density 0.406%

references to written works and publications

No Comments

No Known Activations

references to written works and publications

No Comments

No Known Activations