INDEX

Explanations

references to the word "Et" or variations of it in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 pred

-0.15

erator

-0.15

ottes

-0.15

LAY

-0.15

aceutical

-0.15

Rim

-0.15

 Purchase

-0.14

andy

-0.14

ulet

-0.14

 Completed

-0.14

POSITIVE LOGITS

ymology

0.28

ihad

0.24

iology

0.23

ablish

0.22

ienne

0.22

iological

0.21

ernity

0.21

ching

0.21

ym

0.21

ched

0.21

Activations Density 0.016%

references to the word "Et" or variations of it in different contexts

No Comments

No Known Activations