INDEX

Explanations

variations of the word "some."

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

oppers

-0.17

eous

-0.16

ivot

-0.15

overy

-0.15

eos

-0.15

ymm

-0.15

yonel

-0.14

yms

-0.14

ÑģÑĤÐ°

-0.14

sik

-0.14

POSITIVE LOGITS

ewhere

0.32

brero

0.30

ewhat

0.29

erville

0.27

erset

0.26

etime

0.26

mers

0.25

thing

0.23

ETIME

0.22

ber

0.21

Activations Density 0.008%

variations of the word "some."

No Comments

No Known Activations