INDEX

Explanations

locations and their significance

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

ulk

-0.16

adro

-0.15

rypton

-0.14

 snap

-0.14

èĩ£

-0.14

 travel

-0.13

 head

-0.13

Inv

-0.13

 quiet

-0.13

iro

-0.13

POSITIVE LOGITS

gba

0.16

 Entire

0.15

usal

0.15

 nationwide

0.14

 entire

0.14

habi

0.14

orp

0.14

elter

0.14

IfExists

0.14

Activations Density 0.036%

locations and their significance

No Comments

No Known Activations