INDEX

Explanations

classes and structural components 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

 ByVal

-0.17

isd

-0.15

enti

-0.15

oe

-0.15

ua

-0.15

aris

-0.14

ploy

-0.14

vit

-0.13

els

-0.13

åī£

-0.13

POSITIVE LOGITS

 convenience

0.24

Wr

0.22

 wrapper

0.19

 Convenience

0.19

 helper

0.19

 convenient

0.19

 abstraction

0.19

Wr

0.19

 abstract

0.18

 helpers

0.18

Activations Density 0.122%

classes and structural components in code documentation

No Comments

No Known Activations