INDEX

Explanations

references to forms and form-related concepts within a coding or application context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

emas

-0.21

 formally

-0.16

foil

-0.16

IAL

-0.15

grams

-0.15

esis

-0.15

 formal

-0.15

ary

-0.15

weep

-0.15

Forms

-0.15

POSITIVE LOGITS

idable

0.32

ulary

0.31

ulating

0.31

ulates

0.27

ulas

0.27

íĥľ

0.27

ulario

0.26

ative

0.25

atted

0.25

atters

0.25

Activations Density 0.061%

references to forms and form-related concepts within a coding or application context

No Comments

No Known Activations