INDEX

Explanations

phrases related to the start and end points in time or processes

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

iew

-0.15

kening

-0.14

ucky

-0.14

illon

-0.14

Floor

-0.13

Ø§ÙĤ

-0.13

quez

-0.13

ÐµÐºÑĤÐ¸Ð²

-0.13

leen

-0.13

 Floor

-0.13

POSITIVE LOGITS

Ãºsqueda

0.18

aines

0.15

izo

0.15

ersh

0.15

agher

0.15

ernals

0.14

.twitch

0.14

umen

0.13

viz

0.13

erdem

0.13

Activations Density 0.085%

phrases related to the start and end points in time or processes

No Comments

No Known Activations