INDEX

Explanations

specific terms related to education, health, and law

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

ıi

-0.15

jian

-0.14

 Hemp

-0.14

riday

-0.14

IVES

-0.14

elen

-0.14

elson

-0.13

ASP

-0.13

POSITIVE LOGITS

atron

0.16

æĲŃ

0.15

oring

0.14

ynes

0.14

Ð¹Ð½

0.14

è¶Ĭ

0.14

áº¿

0.14

Ã¤llt

0.14

 kayn

0.14

.YesNo

0.13

Activations Density 0.510%

specific terms related to education, health, and law

No Comments

No Known Activations