INDEX

Explanations

references to registration, accessibility, and participation in various contexts

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

ramework

-0.14

stroy

-0.12

ividad

-0.12

chyb

-0.12

osph

-0.11

chedulers

-0.11

coni

-0.11

emme

-0.11

lest

-0.11

 âĸĳ

-0.11

POSITIVE LOGITS

now

1.43

now

1.15

Now

0.99

 ÑĤÐµÐ¿ÐµÑĢÑĮ

0.98

NOW

0.95

 ahora

0.94

Now

0.93

-now

0.93

_now

0.88

 maintenant

0.87

Activations Density 0.667%

references to registration, accessibility, and participation in various contexts

No Comments

No Known Activations

references to registration, accessibility, and participation in various contexts

No Comments

No Known Activations