INDEX

Explanations

references to governmental actions and policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ampo

-0.15

SEN

-0.15

fak

-0.14

pez

-0.14

aks

-0.13

ugu

-0.13

ãĥ¥

-0.13

ivot

-0.13

ady

-0.13

âĺĨ

-0.13

POSITIVE LOGITS

 government

0.84

 Government

0.71

government

0.71

æĶ¿åºľ

0.67

Government

0.64

 governments

0.60

-government

0.57

 governo

0.55

 gobierno

0.52

 à¤¸à¤°à¤ķ

0.50

Activations Density 0.269%

references to governmental actions and policies

No Comments

No Known Activations