INDEX

Explanations

references to historical success or established track records

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ews

-0.16

Ã¡zi

-0.14

_aspect

-0.14

ething

-0.14

®¤

-0.14

lsen

-0.13

thes

-0.13

abez

-0.13

outu

-0.13

ulf

-0.13

POSITIVE LOGITS

/history

0.22

 history

0.20

istory

0.19

(history

0.18

-history

0.18

 Geschichte

0.17

ÚĨÙĩ

0.17

history

0.16

 histories

0.16

 HISTORY

0.15

Activations Density 0.074%

references to historical success or established track records

No Comments

No Known Activations