INDEX

Explanations

words and phrases associated with connections or relationships between entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

elder

-0.18

ase

-0.15

er

-0.14

 Ð¿Ð¾ÑĤ

-0.14

illo

-0.14

ÑĥÑĢÐ°

-0.13

erville

-0.13

EM

-0.13

ulet

-0.13

nh

-0.13

POSITIVE LOGITS

lÃŃ

0.17

æĿī

0.15

Ðĩ

0.14

é³´

0.14

uchar

0.14

utsch

0.14

VERRIDE

0.14

_pag

0.14

/MPL

0.14

_MC

0.13

Activations Density 0.120%

words and phrases associated with connections or relationships between entities

No Comments

No Known Activations