INDEX

Explanations

references to American identity and its historical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ivism

-0.17

 nejvÄĽtÅ¡ÃŃ

-0.15

ustria

-0.14

 addCriterion

-0.14

onica

-0.14

ismu

-0.14

à¹ĳ

-0.14

SWEP

-0.13

chemy

-0.13

.CreateCommand

-0.13

POSITIVE LOGITS

 psyche

0.27

 experience

0.25

 populace

0.24

 penchant

0.24

 experiment

0.23

 imagination

0.23

 electorate

0.23

 establishment

0.23

way

0.23

 version

0.22

Activations Density 0.131%

references to American identity and its historical context

No Comments

No Known Activations