INDEX

Explanations

technical terms and details related to aviation and aerospace testing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

elmet

-0.19

 æ±Ł

-0.15

caff

-0.14

 LÃ¢m

-0.14

uds

-0.13

edis

-0.13

ª

-0.13

aub

-0.13

illo

-0.13

gÃ¼n

-0.13

POSITIVE LOGITS

yn

0.15

osp

0.15

odash

0.14

chie

0.14

anel

0.14

 McGu

0.14

ato

0.14

:href

0.14

olk

0.13

Ð°ÑĤÐ¾

0.13

Activations Density 0.021%

technical terms and details related to aviation and aerospace testing

No Comments

No Known Activations