INDEX

Explanations

items relating to electronic signals and indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

hardt

-0.15

lund

-0.14

æ¥Ń

-0.14

(~(

-0.13

opoly

-0.13

ocale

-0.13

rade

-0.13

riot

-0.13

kl

-0.13

otte

-0.13

POSITIVE LOGITS

 indicating

0.18

 indication

0.17

 indicates

0.17

wap

0.17

indic

0.17

 indications

0.17

apan

0.16

PathParam

0.14

 sign

0.14

RowAt

0.14

Activations Density 0.085%

items relating to electronic signals and indicators

No Comments

No Known Activations