INDEX

Explanations

the word "typical" 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

rp

-0.19

our

-0.17

ined

-0.17

eron

-0.17

blings

-0.16

to

-0.15

adi

-0.15

tu

-0.15

æĪ

-0.15

inta

-0.15

POSITIVE LOGITS

ity

0.24

 xuyÃªn

0.23

mente

0.21

weise

0.20

ITY

0.19

TEGER

0.18

ewise

0.17

ALLY

0.17

wealth

0.16

ily

0.16

Activations Density 0.018%

the word "typical" and its variations

No Comments

No Known Activations