INDEX

Explanations

references to inmates or the incarcerated population

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

esl

-0.15

mez

-0.15

 Grat

-0.14

awl

-0.14

izo

-0.14

 Imper

-0.14

 Rodrig

-0.14

Mez

-0.14

.UIManager

-0.13

QP

-0.13

POSITIVE LOGITS

orable

0.16

orca

0.16

fish

0.15

ox

0.14

ex

0.14

Experts

0.14

 kole

0.14

orang

0.14

AFE

0.14

ãĥ³ãĤ¹

0.14

Activations Density 0.005%

references to inmates or the incarcerated population

No Comments

No Known Activations