INDEX

Explanations

references to blog entries and their associated tags

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

-0.16

uchs

-0.15

ucher

-0.15

IFO

-0.14

 authorities

-0.14

antu

-0.14

brero

-0.14

ãģĵãģĿ

-0.14

andex

-0.14

POSITIVE LOGITS

 Weston

0.15

azu

0.14

>({

0.14

mps

0.14

sic

0.14

ç

0.14

abinet

0.14

geber

0.14

/full

0.14

abin

0.14

Activations Density 0.004%

references to blog entries and their associated tags

No Comments

No Known Activations