INDEX

Explanations

mentions of occupations and roles, particularly in professional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

mej

-0.16

-0.14

iant

-0.14

uko

-0.14

echa

-0.14

opak

-0.14

iene

-0.14

Multiplicity

-0.13

Cv

-0.13

ycz

-0.13

POSITIVE LOGITS

she

0.19

 ê·¸ëĬĶ

0.18

 à¤īà¤¸à¤¨

0.17

Î½Ïī

0.16

 saya

0.16

 usted

0.15

he

0.15

you

0.15

 Ð¾Ð½Ð°

0.15

ogan

0.15

Activations Density 0.175%

mentions of occupations and roles, particularly in professional contexts

No Comments

No Known Activations