INDEX

Explanations

assertions or claims about principles, ethics, and guidelines

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

JNI

-0.16

 darken

-0.15

ci

-0.14

PG

-0.14

esModule

-0.14

Zar

-0.14

Pry

-0.13

æĪ¸

-0.13

ordo

-0.13

_based

-0.13

POSITIVE LOGITS

apus

0.17

à¸¥à¸ĩ

0.16

0.15

0.14

Ø±Ø§Ø¯

0.14

Ø§ÙĪÙĬ

0.14

Activations Density 0.147%

assertions or claims about principles, ethics, and guidelines

No Comments

No Known Activations