INDEX

Explanations

questions about locations or directions

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

olic

-0.15

ancel

-0.14

borg

-0.13

ÐµÐ±

-0.13

strict

-0.13

ilar

-0.13

Hem

-0.13

spin

-0.13

éģĵ

-0.13

Disclaimer

-0.13

POSITIVE LOGITS

Where

0.17

 Where

0.17

(where

0.16

ä½įæĸ¼

0.15

 ÙĤØ±Ø§Ø±

0.15

nist

0.14

esso

0.14

è¸ı

0.14

.radians

0.14

UG

0.14

Activations Density 0.102%

questions about locations or directions

No Comments

No Known Activations