INDEX

Explanations

references to influential political figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 Ultr

-0.16

erez

-0.16

 Farage

-0.15

 Isle

-0.15

Ø¬ÙĨ

-0.14

 Infinity

-0.14

ensor

-0.14

igon

-0.14

Î´Î·

-0.13

POSITIVE LOGITS

 Oval

0.22

 presidents

0.21

 President

0.21

 misunder

0.20

 presidency

0.20

 president

0.19

 Presidency

0.19

 Presidents

0.19

 presidential

0.18

 Bush

0.18

Activations Density 0.108%

references to influential political figures

No Comments

No Known Activations