INDEX

Explanations

references to various websites and their rankings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

loe

-0.19

mente

-0.18

wig

-0.17

soever

-0.16

rc

-0.16

nt

-0.16

stood

-0.16

lder

-0.16

OAD

-0.16

lie

-0.15

POSITIVE LOGITS

lessly

0.20

-packages

0.18

izens

0.16

advisor

0.16

geist

0.16

-wide

0.16

/app

0.16

erville

0.15

iors

0.15

elli

0.15

Activations Density 0.058%

references to various websites and their rankings

No Comments

No Known Activations