INDEX

Explanations

words and phrases indicating processes related to making decisions or collaborations

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

iga

-0.15

bow

-0.15

respons

-0.14

ody

-0.13

éľĬ

-0.13

 richest

-0.13

âĪ¨

-0.13

 Yard

-0.13

 calling

-0.12

POSITIVE LOGITS

CompleteListener

0.14

askell

0.14

Ars

0.14

_consts

0.13

lep

0.13

ÂŃtion

0.13

 Pell

0.13

 Parkinson

0.13

angkan

0.13

Activations Density 0.071%

words and phrases indicating processes related to making decisions or collaborations

No Comments

No Known Activations