INDEX

Explanations

phrases that involve the concept of connections or associations

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

.scala

-0.15

_ISO

-0.15

Ð°ÑĢÑĩ

-0.15

Ãłng

-0.14

	Copyright

-0.14

etre

-0.14

iom

-0.14

ilog

-0.14

chluss

-0.14

.SDK

-0.14

POSITIVE LOGITS

 disqualified

0.15

Soy

0.14

 Hath

0.14

enville

0.14

 Chap

0.13

ILD

0.13

pun

0.13

labs

0.13

erp

0.13

roid

0.13

Activations Density 0.280%

phrases that involve the concept of connections or associations

No Comments

No Known Activations