INDEX

Explanations

punctuation, specifically periods, commas, and semicolons, indicating sentence boundaries and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

eil

-0.16

hang

-0.15

Ã¤nn

-0.15

enville

-0.13

eyJ

-0.13

 Myers

-0.13

PropTypes

-0.13

 TÃ¢n

-0.13

errick

-0.13

ÑĮÑİ

-0.13

POSITIVE LOGITS

cud

0.15

iland

0.15

adian

0.15

atica

0.14

oug

0.14

ikh

0.14

atical

0.14

aticon

0.14

 Laguna

0.14

abr

0.14

Activations Density 0.019%

punctuation, specifically periods, commas, and semicolons, indicating sentence boundaries and structure

No Comments

No Known Activations