INDEX

Explanations

instances of the word "grant" or its variations, particularly in contexts related to legal or official permissions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

eldorf

-0.17

lej

-0.16

hei

-0.16

hrad

-0.16

yor

-0.15

iminal

-0.15

è¬

-0.15

loff

-0.15

ounty

-0.14

 è³

-0.14

POSITIVE LOGITS

WEST

0.16

äºĪ

0.16

IX

0.15

 MetroFramework

0.14

 Kong

0.14

ushman

0.14

 kepada

0.14

aat

0.14

ree

0.14

roys

0.14

Activations Density 0.049%

instances of the word "grant" or its variations, particularly in contexts related to legal or official permissions

No Comments

No Known Activations