INDEX

Explanations

programming and coding-related terms and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

iente

-0.16

acht

-0.16

ÑĪÐµÐ²

-0.15

-Cal

-0.14

zan

-0.14

 lÃ²ng

-0.14

ODO

-0.14

enu

-0.14

iday

-0.14

ules

-0.14

POSITIVE LOGITS

able

0.26

abler

0.19

ABLE

0.18

ables

0.18

ä¸įäºĨ

0.16

abled

0.16

ability

0.16

nable

0.16

gable

0.15

abl

0.15

Activations Density 0.198%

programming and coding-related terms and functions

No Comments

No Known Activations