INDEX

Explanations

locations and addresses associated with various entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

-0.17

-0.16

-0.15

 crush

-0.15

-0.14

 ming

-0.14

POSITIVE LOGITS

ADDRESS

0.23

 address

0.23

 located

0.22

 ADDRESS

0.21

address

0.20

 corner

0.20

 Address

0.20

Activations Density 0.147%

locations and addresses associated with various entities

No Comments

No Known Activations