INDEX

Explanations

content that is perceived as unengaging or lacking excitement

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

mad

-0.14

Ill

-0.14

itlement

-0.13

omap

-0.13

ÙĦÙĩ

-0.13

éĢ¸

-0.13

bare

-0.12

å±±å¸Ĥ

-0.12

atile

-0.12

 Roland

-0.12

POSITIVE LOGITS

 boring

0.30

åĳ³

0.21

slow

0.19

 dull

0.18

 tedious

0.17

_slow

0.17

 monot

0.17

 slow

0.17

dr

0.16

ARRIER

0.16

Activations Density 0.066%

content that is perceived as unengaging or lacking excitement

No Comments

No Known Activations