INDEX

Explanations

references to historical political events and regimes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ahoma

-0.15

 Copenhagen

-0.15

morgan

-0.15

é¼»

-0.14

TSA

-0.14

VERTISE

-0.14

imuth

-0.13

enza

-0.13

 Cunning

-0.13

POSITIVE LOGITS

 fasc

0.38

 Fasc

0.36

 Muss

0.32

 fascism

0.29

 fascist

0.29

0.26

 Franco

0.24

Fal

0.24

Fal

0.24

 Hitler

0.23

Activations Density 0.015%

references to historical political events and regimes

No Comments

No Known Activations