INDEX

Explanations

phrases related to policies and regulations within institutional frameworks

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

 benches

-0.15

eming

-0.15

ilty

-0.14

 Manson

-0.14

abin

-0.14

æĪĲ

-0.14

 bench

-0.14

 nevid

-0.14

ÐµÐ»Ñĸ

-0.14

Mb

-0.14

POSITIVE LOGITS

ikut

0.18

ibel

0.17

adoo

0.16

ikh

0.14

vik

0.14

coln

0.14

eyse

0.14

 milan

0.14

ikel

0.14

 æ¥

0.13

Activations Density 0.218%

phrases related to policies and regulations within institutional frameworks

No Comments

No Known Activations