INDEX

Explanations

mentions of the name "Stephen" 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 @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

sey

-0.15

baum

-0.15

omas

-0.15

avir

-0.14

ogle

-0.14

ADER

-0.14

essel

-0.14

lege

-0.14

OptionsMenu

-0.14

iber

-0.14

POSITIVE LOGITS

ania

0.23

ansson

0.22

anie

0.19

enson

0.18

Ø§ÙĨÙĪ

0.17

enville

0.16

opoulos

0.16

ano

0.16

hil

0.15

edium

0.15

Activations Density 0.007%

mentions of the name "Stephen" and its variations

No Comments

No Known Activations