INDEX

Explanations

punctuation and syntax elements in code-like structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

qed

-0.16

implify

-0.15

Ã¢ce

-0.14

utenberg

-0.14

MLS

-0.14

Ø¨Ø´

-0.14

ilim

-0.14

alto

-0.14

 OTHERWISE

-0.13

&action

-0.13

POSITIVE LOGITS

.openConnection

0.15

 Trev

0.14

 ÑĥÐ¿

0.14

reet

0.14

alis

0.14

ÂĿ

0.13

 sposÃ³b

0.13

aname

0.13

 gist

0.13

Ã³l

0.13

Activations Density 0.147%

punctuation and syntax elements in code-like structures

No Comments

No Known Activations