INDEX

Explanations

instances of the word "extensive" and its variations

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

ispers

-0.19

se

-0.16

sworth

-0.16

ê»ĺ

-0.15

umann

-0.15

ILLISE

-0.15

lectric

-0.15

venes

-0.15

heim

-0.15

izable

-0.14

POSITIVE LOGITS

ively

0.23

 amounts

0.22

amount

0.19

 amount

0.17

iveness

0.17

-ranging

0.17

overlap

0.17

-scale

0.16

 Amount

0.15

Ú¯ÛĮØ±

0.15

Activations Density 0.033%

instances of the word "extensive" and its variations

No Comments

No Known Activations