INDEX

Explanations

elements related to academic or scientific references, particularly in the context of biology and related areas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

and

-0.30

in

-0.28

-0.27

on

-0.26

the

-0.26

at

-0.26

of

-0.26

to

-0.26

POSITIVE LOGITS

ournals

0.31

ä»¬

0.31

agrams

0.30

embros

0.29

ramids

0.28

ÙĬØ§Øª

0.27

ystals

0.27

endars

0.27

semblies

0.27

dictions

0.27

Activations Density 0.068%

elements related to academic or scientific references, particularly in the context of biology and related areas

No Comments

No Known Activations