INDEX

Explanations

elements indicating the structure of a software artifact or dependency configuration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ivor

-0.17

retty

-0.17

Å¡k

-0.15

Ð½Ð¾Ð¿

-0.14

uler

-0.14

 Sesso

-0.14

ÐµÑĢÑĤ

-0.14

oop

-0.14

olet

-0.14

esi

-0.14

POSITIVE LOGITS

 Nolan

0.13

 Flood

0.13

appl

0.13

ustry

0.13

dddd

0.13

leta

0.13

 Hung

0.13

èĤĸ

0.13

Activations Density 0.004%

elements indicating the structure of a software artifact or dependency configuration

No Comments

No Known Activations