INDEX

Explanations

details related to events and their locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Harvard

-0.26

 Yale

-0.22

 Cambridge

-0.19

 Princeton

-0.18

 Cornell

-0.18

UCS

-0.17

 Columbia

-0.16

 Charlottesville

-0.16

 Vanderbilt

-0.16

 Oxford

-0.15

POSITIVE LOGITS

coe

0.17

 Buccane

0.16

utenberg

0.15

áº¡c

0.15

iou

0.15

cean

0.14

.validate

0.14

iences

0.14

cheon

0.14

itial

0.13

Activations Density 0.201%

details related to events and their locations

No Comments

No Known Activations

details related to events and their locations

No Comments

No Known Activations