INDEX

Explanations

references to opposing parties or sides in a debate or conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ÑĥÑħ

-0.16

ippet

-0.15

ovah

-0.15

uckle

-0.15

ç»Ī

-0.14

èĪŀ

-0.14

entai

-0.14

uckles

-0.14

ennon

-0.14

adle

-0.14

POSITIVE LOGITS

.EventArgs

0.18

akin

0.16

Jab

0.16

opl

0.15

argin

0.14

dk

0.14

quil

0.14

ively

0.14

Activations Density 0.109%

references to opposing parties or sides in a debate or conflict

No Comments

No Known Activations