INDEX

Explanations

references to emergency response and search operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

istrovstvÃŃ

-0.16

_INLINE

-0.16

 sense

-0.15

çª

-0.15

alach

-0.15

 perfume

-0.14

 steward

-0.14

 Tick

-0.14

 Ð·Ð°ÐºÐ»Ð°Ð´

-0.14

âĶ´

-0.14

POSITIVE LOGITS

poser

0.15

posables

0.14

_simps

0.14

eq

0.14

 twisted

0.14

Dal

0.13

ä¿Ĺ

0.13

 Milan

0.13

 Blizzard

0.13

 Ø§ØµÙĦ

0.13

Activations Density 0.092%

references to emergency response and search operations

No Comments

No Known Activations