INDEX

Explanations

assignments and evaluations in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

leigh

-0.18

nelle

-0.16

ucci

-0.16

 offsetof

-0.16

uze

-0.15

leon

-0.15

ÙĪØ§Ø¡

-0.15

onne

-0.14

ister

-0.14

Ø±Ø³

-0.14

POSITIVE LOGITS

ervisor

0.15

icket

0.14

åĸ

0.14

ahlen

0.14

skill

0.14

anger

0.14

sup

0.14

anco

0.13

Wik

0.13

Mov

0.13

Activations Density 0.051%

assignments and evaluations in programming code

No Comments

No Known Activations