INDEX

Explanations

violence and crime

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L11R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Hzfinfdu/SlimPajama-3B and open-r1/OpenR1-Math-220k

Features

32,768

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dera

-0.07

licit

-0.06

eras

-0.06

Unified

-0.06

UPI

-0.06

-sama

-0.06

jec

-0.06

imei

-0.06

acre

-0.06

olis

-0.06

POSITIVE LOGITS

 provided

0.06

kay

0.06

ixer

0.06

ãĥ¼ãĥ«

0.06

provided

0.06

and

0.06

pr

0.06

 lidi

0.06

immer

0.05

lee

0.05

Activations Density 0.180%

violence and crime

No Comments

No Known Activations