INDEX

Explanations

references to specific individuals and their relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Sham

-0.17

_HDR

-0.17

 reserv

-0.16

³

-0.16

 Char

-0.16

ÑĤÐ¾Ð²

-0.15

itial

-0.15

Ã´

-0.15

 promin

-0.15

å¸

-0.15

POSITIVE LOGITS

 Romanian

0.38

 Romania

0.35

Äĥ

0.30

cea

0.28

 Buch

0.26

.ro

0.25

Roman

0.24

ÈĻ

0.23

radu

0.23

 pentru

0.22

Activations Density 0.221%

references to specific individuals and their relationships

No Comments

No Known Activations