INDEX

Explanations

references to the term "Bot" and related entities

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

-0.18

es

-0.18

oth

-0.17

hip

-0.15

hurst

-0.15

slide

-0.14

ianne

-0.14

Ø«

-0.14

oice

-0.14

POSITIVE LOGITS

swana

0.38

anical

0.37

ched

0.28

tega

0.27

any

0.24

anic

0.23

.bot

0.20

CHED

0.20

anik

0.20

leneck

0.19

Activations Density 0.008%

references to the term "Bot" and related entities

No Comments

No Known Activations