INDEX

Explanations

specific procedural or data-related elements in formal documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

etto

-0.18

ichen

-0.16

ı

-0.15

onda

-0.15

erland

-0.14

insky

-0.14

ãĥ³ãĤ°

-0.14

ONSE

-0.14

icho

-0.14

Ø©

-0.14

POSITIVE LOGITS

fred

0.15

xCA

0.14

ÐºÑĥÑĢ

0.14

ulen

0.14

ÐºÐ°Ð²

0.14

ÂŃs

0.14

owi

0.13

imers

0.13

ksi

0.13

stable

0.13

Activations Density 0.005%

specific procedural or data-related elements in formal documents

No Comments

No Known Activations