INDEX

Explanations

the presence and frequency of the word "words" and its variations 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 @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

iders

-0.18

imson

-0.16

idders

-0.16

yang

-0.15

ãģŀ

-0.15

oter

-0.15

ees

-0.15

quet

-0.14

embr

-0.14

/catalog

-0.14

POSITIVE LOGITS

mith

0.30

/ph

0.24

play

0.19

-picture

0.19

robe

0.18

 konusu

0.18

éĶĭ

0.17

worth

0.16

regor

0.16

ake

0.16

Activations Density 0.054%

the presence and frequency of the word "words" and its variations in different contexts

No Comments

No Known Activations