INDEX

Explanations

phrases that indicate emotional or existential reflection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Morg

-0.20

 ÐļÐ¸ÑĶ

-0.17

 Fresno

-0.15

ernes

-0.15

MG

-0.15

arasÄ±

-0.14

hive

-0.14

hood

-0.14

çıł

-0.14

nest

-0.14

POSITIVE LOGITS

ham

1.33

 Hamilton

1.31

Ham

1.31

Ham

1.21

ham

1.15

Hamilton

1.12

.ham

1.07

HAM

1.02

 Hammer

0.94

 hammer

0.88

Activations Density 0.044%

phrases that indicate emotional or existential reflection

No Comments

No Known Activations