INDEX

Explanations

phrases related to rules and regulations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ãĥ«ãĥĪ

-0.16

_mD

-0.15

edException

-0.15

_tE

-0.15

acades

-0.14

apore

-0.14

alore

-0.14

 Ð¿Ð»Ð¸ÑĤ

-0.14

%B

-0.14

Ð¸ÑģÐ»Ð¾Ð²

-0.14

POSITIVE LOGITS

umber

0.16

 other

0.16

 similarly

0.15

 likewise

0.15

 naopak

0.14

bie

0.14

¤

0.14

imilar

0.14

 others

0.14

dit

0.14

Activations Density 0.336%

phrases related to rules and regulations in various contexts

No Comments

No Known Activations