INDEX

Explanations

references to levels of governance and administration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

enburg

-0.15

loff

-0.15

THR

-0.15

enge

-0.15

-0.14

ibe

-0.14

äº

-0.14

kenin

-0.14

chÃ©

-0.14

gaard

-0.14

POSITIVE LOGITS

 macro

0.30

 micro

0.29

 macros

0.28

 grass

0.28

macro

0.25

 local

0.25

 national

0.24

micro

0.24

mes

0.24

 grassroots

0.24

Activations Density 0.067%

references to levels of governance and administration

No Comments

No Known Activations