INDEX

Explanations

structured programming concepts and elements in code documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

enci

-0.15

 Mitar

-0.15

asco

-0.15

 nuru

-0.14

 varargin

-0.14

atty

-0.14

CDATA

-0.14

 CascadeType

-0.13

Ð¾ÑģÐ¿

-0.13

POSITIVE LOGITS

deme

0.15

olini

0.15

hol

0.15

0.14

 Lump

0.14

 \↵

0.14

avana

0.13

 meeting

0.13

ÑģÑĤÐ²ÐµÐ½

0.13

Activations Density 0.011%

structured programming concepts and elements in code documentation

No Comments

No Known Activations