INDEX

Explanations

references to victimization and oppression

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

YLE

-0.16

-0.15

 Imper

-0.14

SCR

-0.14

Sik

-0.14

 Sick

-0.14

sey

-0.14

 agendas

-0.14

alf

-0.13

luk

-0.13

POSITIVE LOGITS

éģĩ

0.15

ĳľ

0.15

edException

0.15

ooter

0.15

kate

0.14

dealloc

0.14

USTER

0.14

udi

0.14

ovny

0.14

orte

0.13

Activations Density 0.436%

references to victimization and oppression

No Comments

No Known Activations