INDEX

Explanations

prepositions and descriptors related to location and positioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Ø§ÙĦØ£ÙĨ

-0.15

care

-0.14

éĢ¸

-0.14

SETTINGS

-0.14

abela

-0.13

Merit

-0.13

iler

-0.13

ilip

-0.13

aisy

-0.13

POSITIVE LOGITS

rani

0.15

CTION

0.15

">//

0.14

Endian

0.14

 æĪ

0.14

asha

0.14

Ãª

0.14

oje

0.13

 Hose

0.13

aan

0.13

Activations Density 0.172%

prepositions and descriptors related to location and positioning

No Comments

No Known Activations