INDEX

Explanations

proper nouns, particularly names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

urtle

-0.15

 abbrev

-0.15

-0.14

-thumbnails

-0.14

odus

-0.13

vie

-0.13

kup

-0.13

-bootstrap

-0.13

 Brief

-0.13

_prep

-0.13

POSITIVE LOGITS

 family

0.20

-family

0.17

æ°ı

0.15

 clan

0.15

family

0.15

 Family

0.15

 FAMILY

0.15

Ø§ÙĨÙĪ

0.15

ikut

0.15

.SDK

0.15

Activations Density 0.156%

proper nouns, particularly names of individuals

No Comments

No Known Activations