INDEX

Explanations

phrases and terms indicating political preferences and positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

.WebControls

-0.14

æĹ¦

-0.14

fec

-0.14

BU

-0.14

 Pension

-0.14

.gstatic

-0.14

èķī

-0.14

cal

-0.14

 alacak

-0.14

 exerc

-0.14

POSITIVE LOGITS

ÑĢÐ°Ð²Ð°

0.19

kers

0.17

aniem

0.16

anks

0.15

kker

0.15

ikk

0.15

.central

0.15

odka

0.14

 bins

0.14

abama

0.14

Activations Density 0.795%

phrases and terms indicating political preferences and positions

No Comments

No Known Activations