INDEX

Explanations

references to physical locations, particularly houses and homes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 yÃ¼z

-0.15

Ð¸ÑĤÐ¾Ð¼

-0.15

enis

-0.15

enheim

-0.15

parer

-0.14

Î½Î¿Ïį

-0.14

ÏĦÎ¿Ïį

-0.14

prite

-0.14

.infinity

-0.14

 Smart

-0.14

POSITIVE LOGITS

field

0.18

 Kramer

0.17

 defaultManager

0.16

psilon

0.16

strup

0.15

Eug

0.14

tÃŃ

0.14

ÐºÐ¾Ð²Ð¾

0.14

à¸±à¸Ļà¸¡

0.14

Activations Density 0.367%

references to physical locations, particularly houses and homes

No Comments

No Known Activations