INDEX

Explanations

geographic references and locations

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

opus

-0.15

erosis

-0.14

&_

-0.14

 disc

-0.14

rÃ¥

-0.14

pus

-0.13

riers

-0.13

ongoose

-0.13

rÃ³

-0.13

ronics

-0.13

POSITIVE LOGITS

 satellite

0.22

 Satellite

0.21

sat

0.20

 street

0.19

.sat

0.18

 STREET

0.17

 Street

0.17

Street

0.17

sat

0.17

 Bing

0.16

Activations Density 0.008%

geographic references and locations

No Comments

No Known Activations