INDEX

Explanations

patterns or structures in numerical data and measurements

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

zan

-0.16

utzer

-0.14

 Discovery

-0.14

FD

-0.14

çĽ¤

-0.14

aggi

-0.14

ril

-0.14

Å¡ek

-0.13

BY

-0.13

_PF

-0.13

POSITIVE LOGITS

æ½

0.14

.ef

0.14

 ãĤ½

0.14

Ð°Ð¹ÑĤ

0.14

æĭ¥

0.14

alc

0.13

alty

0.13

æ°´å¹³

0.13

 Salem

0.13

.tap

0.13

Activations Density 0.194%

patterns or structures in numerical data and measurements

No Comments

No Known Activations