INDEX

Explanations

words related to war and honoring those involved

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

Ð¾Ð±Ð¾Ð²

-0.08

piv

-0.07

ire

-0.06

ect

-0.06

olk

-0.06

zza

-0.06

GAN

-0.06

bor

-0.06

ensem

-0.06

(en

-0.06

POSITIVE LOGITS

âĦĸâĦĸ

0.09

ÐĲÑĢÑħÑĸÐ²

0.08

afari

0.08

ishop

0.07

CHIP

0.07

Byl

0.07

_statuses

0.06

.createObject

0.06

oriented

0.06

ichen

0.06

Activations Density 0.075%

words related to war and honoring those involved

No Comments

No Known Activations