INDEX

Explanations

references to storage cabinets and organizational products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

isz

-0.14

´Ī

-0.13

 dÃ¼r

-0.13

Mt

-0.13

 worker

-0.13

resh

-0.13

Å¼

-0.13

rouch

-0.12

Synopsis

-0.12

 :↵

-0.12

POSITIVE LOGITS

uk

0.20

UK

0.19

 Canada

0.19

 Near

0.17

 Lowe

0.17

 Amazon

0.17

 amazon

0.17

.ca

0.16

 Ireland

0.16

Canada

0.16

Activations Density 0.019%

references to storage cabinets and organizational products

No Comments

No Known Activations