INDEX

Explanations

code-related terms and structure, particularly related to imports and function definitions 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 @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

[{'

-0.19

[{"

-0.18

otics

-0.16

#{

-0.15

YRO

-0.15

 Blanco

-0.15

Ë

-0.14

â

-0.14

ripper

-0.14

 paramMap

-0.14

POSITIVE LOGITS

0.29

0.28

'./

0.26

 {↵

0.26

"./

0.23

 '../

0.23

'@

0.19

Scripts

0.18

 '../../

0.18

 "../

0.18

Activations Density 0.006%

code-related terms and structure, particularly related to imports and function definitions in programming

No Comments

No Known Activations