INDEX

Explanations

references to islands and their descriptions

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

 oceans

-0.16

.safe

-0.15

 ocean

-0.15

 Ocean

-0.15

 Pacific

-0.15

els

-0.15

mir

-0.15

enville

-0.15

vvm

-0.15

Extend

-0.14

POSITIVE LOGITS

 Cors

0.19

 Lesb

0.19

ushima

0.18

Äįer

0.17

 Jersey

0.17

 Hispan

0.17

Cors

0.17

Sic

0.17

 jersey

0.17

 Flores

0.16

Activations Density 0.091%

references to islands and their descriptions

No Comments

No Known Activations