INDEX

Explanations

specific terms related to medical or technical procedures

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/800M-Slimpajama-0-OpenR1-Math-220k/L15R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Hzfinfdu/SlimPajama-3B

Features

32,768

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cth

-0.15

agate

-0.15

isman

-0.14

Ã¼f

-0.14

ÑıÐ½

-0.14

Diagram

-0.13

[:]

-0.13

ÏĢÎ±

-0.13

igar

-0.13

ancell

-0.13

POSITIVE LOGITS

_defaults

0.15

0.14

ardin

0.14

ä¿Ĭ

0.14

æ®Ĭ

0.13

ë¡Ń

0.13

ppo

0.13

 aliment

0.13

mint

0.13

ÎµÎ¹Î¿

0.13

Activations Density 0.243%

specific terms related to medical or technical procedures

No Comments

No Known Activations