INDEX

Explanations

programming-related keywords and concepts, particularly in the context of a class definition or method implementation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

/*č↵

-0.16

ÐºÑĥÑĢ

-0.15

Dispatch

-0.14

ania

-0.14

_FM

-0.14

 Terr

-0.13

rank

-0.13

 Dispatch

-0.13

.fm

-0.13

POSITIVE LOGITS

ucz

0.17

enberg

0.15

ahl

0.15

inement

0.14

wit

0.14

instein

0.14

Roh

0.13

 Back

0.13

chin

0.13

_upgrade

0.13

Activations Density 0.014%

programming-related keywords and concepts, particularly in the context of a class definition or method implementation

No Comments

No Known Activations