INDEX

Explanations

proper nouns and titles related to cultural or artistic entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

hed

-0.16

wyn

-0.16

ÏģÎº

-0.15

.Framework

-0.15

_Framework

-0.14

-*-

-0.14

ÑĢÐ¸Ñĩ

-0.14

afa

-0.14

ndef

-0.14

sea

-0.13

POSITIVE LOGITS

AG

0.25

allee

0.20

und

0.20

 GmbH

0.18

park

0.18

vere

0.17

jug

0.17

mb

0.17

ges

0.17

Bra

0.17

Activations Density 0.153%

proper nouns and titles related to cultural or artistic entities

No Comments

No Known Activations