INDEX

Explanations

references to family and children

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

-Za

-0.16

.nano

-0.15

/XMLSchema

-0.14

lish

-0.14

Ã¼z

-0.14

ortex

-0.14

ÑģÑıÐ³

-0.14

acente

-0.14

onas

-0.14

fcn

-0.14

POSITIVE LOGITS

0.15

 Bund

0.14

 Cham

0.14

_Report

0.14

0.13

Retrieve

0.13

 Bran

0.13

acs

0.13

Ð½ÐµÐ¹

0.13

Activations Density 0.020%

references to family and children

No Comments

No Known Activations