INDEX

Explanations

programming-related keywords and constructs, particularly those associated with data structures and type checking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

asher

-0.17

Î»Î¼

-0.16

idle

-0.14

oins

-0.14

hu

-0.14

imd

-0.14

-demand

-0.14

 FLAG

-0.14

æ´

-0.14

[code

-0.14

POSITIVE LOGITS

Ð±ÐµÑĢ

0.15

arge

0.15

mate

0.14

 Crawford

0.14

Odd

0.14

lyn

0.14

Spl

0.14

mitter

0.14

 Ster

0.14

ellery

0.13

Activations Density 0.030%

programming-related keywords and constructs, particularly those associated with data structures and type checking

No Comments

No Known Activations