INDEX

Explanations

mentions of the word "Van" 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

pon

-0.16

Ð¸ÑĢÐ¾Ð²

-0.15

yps

-0.15

isans

-0.15

achen

-0.15

Ð¸ÐºÑĥ

-0.14

chw

-0.14

tees

-0.14

omes

-0.14

POSITIVE LOGITS

ishing

0.31

adium

0.30

essa

0.27

ished

0.24

ishes

0.22

ISHED

0.21

der

0.20

esa

0.20

ities

0.20

isher

0.19

Activations Density 0.015%

mentions of the word "Van" and its variations

No Comments

No Known Activations