INDEX

Explanations

terms and phrases related to measurement and health-related concerns

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

itto

-0.15

 sclerosis

-0.14

itti

-0.14

uar

-0.14

keh

-0.14

hart

-0.14

upe

-0.14

ochen

-0.14

 Elias

-0.13

reated

-0.13

POSITIVE LOGITS

YPE

0.16

alley

0.15

vida

0.14

ibase

0.14

 Maur

0.14

 Vault

0.14

Projection

0.14

avi

0.14

Ã¼stÃ¼

0.14

 Vaults

0.13

Activations Density 0.001%

terms and phrases related to measurement and health-related concerns

No Comments

No Known Activations