INDEX

Explanations

names of cities, particularly major North American and British locations

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

avan

-0.14

RefCount

-0.14

piel

-0.14

cci

-0.14

 definite

-0.14

Ð»Ð°Ð¼

-0.13

astes

-0.13

 accomplishment

-0.13

anship

-0.13

POSITIVE LOGITS

etc

0.20

Press

0.17

etc

0.16

 ëĵ±ìĿĦ

0.15

éĶĭ

0.15

ALIGN

0.15

0.14

 presses

0.14

 Abrams

0.14

NamedQuery

0.14

Activations Density 0.027%

names of cities, particularly major North American and British locations

No Comments

No Known Activations