INDEX

Explanations

programming-related errors, specifically those related to compilation and exit codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

arium

-0.17

 knight

-0.16

 knights

-0.15

isinde

-0.14

.intellij

-0.14

odcast

-0.14

 Newton

-0.14

Newton

-0.13

inis

-0.13

 linspace

-0.13

POSITIVE LOGITS

 exit

0.47

 Exit

0.45

 EXIT

0.42

Exit

0.42

exit

0.40

EXIT

0.36

 exits

0.36

(exit

0.36

_exit

0.35

.exit

0.34

Activations Density 0.067%

programming-related errors, specifically those related to compilation and exit codes

No Comments

No Known Activations