INDEX

Explanations

references to deserts and related geographical features

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

lish

-0.16

ningen

-0.15

 Salmon

-0.15

sono

-0.14

 trout

-0.14

ÙĬØ¯ÙĬ

-0.14

ISE

-0.13

 ÐĴÐ¸ÐºÐ¸

-0.13

Overflow

-0.13

æł

-0.13

POSITIVE LOGITS

 desert

0.51

 Desert

0.50

 Tucson

0.31

 Sahara

0.30

 Arizona

0.28

 sand

0.28

 Oasis

0.27

 sands

0.26

Arizona

0.26

 Mesa

0.25

Activations Density 0.188%

references to deserts and related geographical features

No Comments

No Known Activations