INDEX

Explanations

references to specific regions and geographical features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Leben

-0.17

 meisje

-0.17

 Unternehmen

-0.17

 Angebot

-0.16

 geil

-0.16

erras

-0.14

strcasecmp

-0.14

å¦ĩ

-0.14

äººæ°ĳ

-0.14

 erotische

-0.14

POSITIVE LOGITS

urovision

0.17

ESÄ°

0.15

inth

0.15

 predecess

0.15

inho

0.15

ALLED

0.14

YGON

0.14

 Golf

0.14

bbie

0.14

oled

0.14

Activations Density 0.085%

references to specific regions and geographical features

No Comments

No Known Activations