INDEX

Explanations

programming language annotations and documentation attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 subsequ

-0.17

Dub

-0.17

 Britt

-0.15

ãĤ¸ãĥ¥

-0.15

fait

-0.15

æĸ¹

-0.14

ras

-0.14

brig

-0.14

elt

-0.14

sealed

-0.14

POSITIVE LOGITS

 Legisl

0.16

ITE

0.16

ISTER

0.15

icode

0.15

 Renderer

0.15

olley

0.14

ena

0.14

 Sentry

0.14

Ģ

0.14

innacle

0.14

Activations Density 0.003%

programming language annotations and documentation attributes

No Comments

No Known Activations