INDEX

Explanations

programming-related keywords and syntax elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

quet

-0.15

unma

-0.15

ething

-0.14

omers

-0.14

zeigen

-0.13

Subjects

-0.13

EntryPoint

-0.13

ÄħÅ¼

-0.13

Hon

-0.13

aptors

-0.13

POSITIVE LOGITS

andal

0.16

PLEX

0.15

SAFE

0.14

luet

0.14

_KERNEL

0.14

æĻĤãģ«

0.14

[property

0.14

æ±¡

0.14

(æ°´

0.14

icont

0.13

Activations Density 0.038%

programming-related keywords and syntax elements

No Comments

No Known Activations