INDEX

Explanations

occurrences of the letter 'z' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

utherford

-0.17

askell

-0.15

ossal

-0.15

mts

-0.15

cheon

-0.14

kek

-0.14

ordova

-0.13

reserve

-0.13

 Gupta

-0.13

akedown

-0.13

POSITIVE LOGITS

ivil

0.27

entral

0.26

eh

0.25

wing

0.24

itat

0.24

uge

0.23

ulet

0.23

umin

0.22

iele

0.22

ahlen

0.22

Activations Density 0.006%

occurrences of the letter 'z' in various contexts

No Comments

No Known Activations