INDEX

Explanations

phrases related to accountability and awareness in various contexts

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

ild

-0.15

isi

-0.15

 fused

-0.14

dash

-0.14

pp

-0.14

achi

-0.14

 inability

-0.13

 Must

-0.13

 must

-0.13

POSITIVE LOGITS

 Proper

0.17

 proper

0.16

è¶³

0.16

proper

0.16

abase

0.15

rende

0.15

enia

0.15

 properly

0.15

 dostat

0.14

 olab

0.14

Activations Density 0.102%

phrases related to accountability and awareness in various contexts

No Comments

No Known Activations