INDEX

Explanations

names and identifiers associated with people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

_FATAL

-0.16

 Ð¶Ðµ

-0.15

by

-0.15

STRUCTIONS

-0.14

èĩ

-0.14

 controlId

-0.14

 æ¬

-0.14

ONTAL

-0.13

 oleh

-0.13

 Ð¿Ð¾Ð·Ð´

-0.13

POSITIVE LOGITS

Contrib

0.27

 Contrib

0.26

contrib

0.26

 contributor

0.24

 CONTRIBUT

0.24

 contributing

0.24

 contributed

0.23

0.22

 Contributor

0.22

Special

0.22

Activations Density 0.069%

names and identifiers associated with people

No Comments

No Known Activations