INDEX

Explanations

references to national or political structures and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

isches

-0.18

licher

-0.18

liches

-0.17

 Ø¢Ø®Ø±

-0.17

erto

-0.17

eres

-0.16

 quello

-0.15

 ÑıÐºÐ¸Ð¹

-0.15

.mj

-0.15

ngen

-0.15

POSITIVE LOGITS

“She

0.26

"She

0.22

elige

0.21

 neue

0.20

 erste

0.19

lige

0.19

 ganze

0.19

 groÃŁe

0.19

 franÃ§aise

0.18

 andere

0.18

Activations Density 0.056%

references to national or political structures and their characteristics

No Comments

No Known Activations