INDEX

Explanations

names of individuals or proper nouns associated with significant contexts, particularly related to legal or political matters

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

 Ð¶Ðµ

-0.16

liness

-0.16

lets

-0.16

ettings

-0.15

amble

-0.14

-Ð·Ð°

-0.14

lit

-0.14

walk

-0.14

ç±į

-0.13

lines

-0.13

POSITIVE LOGITS

çİĩ

0.19

ëıĦ

0.17

ERTICAL

0.16

ubl

0.15

abeth

0.15

vang

0.14

itionally

0.14

à¸¥

0.14

asley

0.14

Activations Density 0.182%

names of individuals or proper nouns associated with significant contexts, particularly related to legal or political matters

No Comments

No Known Activations