INDEX

Explanations

references to health-related organizations or diseases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

wick

-0.18

errupted

-0.14

SGlobal

-0.14

:"-

-0.14

aber

-0.14

ernal

-0.14

 ******************************************************************************↵

-0.14

 Plane

-0.14

/Branch

-0.14

/lic

-0.13

POSITIVE LOGITS

heim

0.15

 inline

0.15

cade

0.15

ested

0.15

uma

0.14

abol

0.14

utron

0.14

umb

0.14

anford

0.13

Activations Density 0.000%

references to health-related organizations or diseases

No Comments

No Known Activations