INDEX

Explanations

references to specific names or terms related to a person's identity or cultural context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Ð»ÑĸÐ´

-0.16

ubb

-0.15

Ã¢ng

-0.15

esktop

-0.15

 Mang

-0.15

angan

-0.15

ITED

-0.15

ilir

-0.15

igham

-0.15

orelease

-0.15

POSITIVE LOGITS

letal

0.20

atchewan

0.18

peare

0.15

ia

0.15

argar

0.14

 heav

0.14

arg

0.14

loff

0.14

iswa

0.14

itr

0.14

Activations Density 0.021%

references to specific names or terms related to a person's identity or cultural context

No Comments

No Known Activations

references to specific names or terms related to a person's identity or cultural context

No Comments

No Known Activations