INDEX

Explanations

references to governmental or authoritative entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

icens

-0.16

Ð»Ð¸ÑĨ

-0.15

anon

-0.14

à¸µà¹Ģà¸Ķ

-0.14

 skies

-0.14

OC

-0.13

ä»²

-0.13

fung

-0.13

oppable

-0.13

missive

-0.13

POSITIVE LOGITS

ibel

0.17

 Digit

0.15

 SAVE

0.14

onte

0.14

fÃ¼hr

0.14

cassert

0.14

arti

0.14

Pry

0.14

_INCREF

0.13

stdexcept

0.13

Activations Density 0.080%

references to governmental or authoritative entities

No Comments

No Known Activations