INDEX

Explanations

references to specific years, particularly those related to historical events or timeframes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

undy

-0.18

idon

-0.16

antium

-0.16

istrov

-0.15

ÃŃr

-0.15

.sourceforge

-0.15

 frau

-0.15

idar

-0.15

á»Ļi

-0.15

.library

-0.14

POSITIVE LOGITS

0.18

ague

0.17

ocs

0.15

į

0.14

yon

0.14

coni

0.14

å¹´ä»£

0.14

 period

0.14

etherlands

0.13

 UserControl

0.13

Activations Density 0.023%

references to specific years, particularly those related to historical events or timeframes

No Comments

No Known Activations