INDEX

Explanations

programming-related terms and phrases associated with application development and debugging

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

adesh

-0.16

INGTON

-0.15

bos

-0.15

ossa

-0.15

iddles

-0.15

ADOR

-0.15

 Associates

-0.15

addin

-0.14

achen

-0.14

esub

-0.14

POSITIVE LOGITS

atoria

0.15

ubar

0.15

 coping

0.14

å¼¥

0.14

ihan

0.14

urai

0.14

lam

0.14

ited

0.14

ILA

0.14

ila

0.14

Activations Density 0.215%

programming-related terms and phrases associated with application development and debugging

No Comments

No Known Activations