INDEX

Explanations

concepts related to authority and governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

è¢«

-0.18

 being

-0.17

è¸ı

-0.17

 ÑģÐµÐ»

-0.16

ettel

-0.16

Receive

-0.15

 become

-0.15

 participate

-0.15

å¼ĺ

-0.15

obili

-0.15

POSITIVE LOGITS

 place

0.20

 Place

0.19

assign

0.18

 allow

0.18

 placing

0.18

 assign

0.17

 award

0.17

 assigning

0.17

 Allow

0.17

Place

0.17

Activations Density 0.414%

concepts related to authority and governance

No Comments

No Known Activations