INDEX

Explanations

technical terms and code-related concepts in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

unas

-0.16

TYPO

-0.15

æŃ

-0.15

è³Ģ

-0.15

 seedu

-0.15

Ú©Ø³

-0.15

amburg

-0.14

 varsa

-0.14

.optional

-0.14

ÐºÑģ

-0.14

POSITIVE LOGITS

zon

0.16

-slot

0.16

Rank

0.15

poi

0.14

 Rank

0.14

 Boys

0.14

errated

0.14

 Lambert

0.14

rade

0.14

 Reed

0.13

Activations Density 0.631%

technical terms and code-related concepts in programming

No Comments

No Known Activations