INDEX

Explanations

references to crises or disasters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

illery

-0.19

weeney

-0.16

endar

-0.15

/Library

-0.14

assage

-0.14

tres

-0.14

ulary

-0.13

irie

-0.13

ason

-0.13

eft

-0.13

POSITIVE LOGITS

 zone

0.28

 scenario

0.27

-hit

0.26

 zones

0.26

 situation

0.26

-str

0.24

 worse

0.23

-zone

0.23

 engulf

0.23

ous

0.23

Activations Density 0.146%

references to crises or disasters

No Comments

No Known Activations