INDEX

Explanations

references to work-related themes and conditions

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

bery

-0.15

 workload

-0.14

inta

-0.14

ãĥ¬ãĤ¹

-0.14

ioneer

-0.14

 Ù¾Ø§Ø³

-0.13

èİ

-0.13

userdata

-0.13

lessly

-0.13

licit

-0.13

POSITIVE LOGITS

-class

0.20

bench

0.19

 Working

0.19

-Class

0.18

-working

0.18

Working

0.17

 working

0.17

quot

0.16

ziel

0.15

éļİ

0.15

Activations Density 0.025%

references to work-related themes and conditions

No Comments

No Known Activations