INDEX

Explanations

words and phrases related to architecture and titles associated with it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

orf

-0.18

zers

-0.17

quot

-0.15

itor

-0.15

osity

-0.14

oil

-0.14

arium

-0.14

arian

-0.14

izer

-0.14

POSITIVE LOGITS

ipel

0.29

itect

0.23

uate

0.20

etypes

0.19

etype

0.19

aic

0.19

angel

0.19

itecture

0.19

bishop

0.18

(es

0.17

Activations Density 0.020%

words and phrases related to architecture and titles associated with it

No Comments

No Known Activations