INDEX

Explanations

instances of incrementing or updating a numerical counter in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

avern

-0.15

olson

-0.15

-return

-0.14

slu

-0.14

Ã´n

-0.14

yps

-0.13

 Geld

-0.13

reste

-0.13

atura

-0.13

POSITIVE LOGITS

ENU

0.16

++)

0.15

##_

0.15

kest

0.15

+=

0.15

ãĤ¢ãĥ¼

0.14

.onView

0.14

ëĵĿ

0.14

å®ı

0.14

Activations Density 0.019%

instances of incrementing or updating a numerical counter in a programming context

No Comments

No Known Activations