INDEX

Explanations

the word "of" in various contexts, often indicating relationships or connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

.scalablytyped

-0.20

asel

-0.18

æ³ī

-0.16

aler

-0.15

ENTE

-0.15

egie

-0.15

ó

-0.14

},'

-0.14

VEC

-0.13

Paz

-0.13

POSITIVE LOGITS

irit

0.17

acy

0.15

ogo

0.14

 Europe

0.14

iaux

0.14

-addons

0.14

Ã¼p

0.14

utton

0.14

 tomorrow

0.14

Activations Density 0.085%

the word "of" in various contexts, often indicating relationships or connections

No Comments

No Known Activations