INDEX

Explanations

references to geometric directions and vectors

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/0-Slimpajama-800M-OpenR1-Math-220k/L15R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

open-r1/OpenR1-Math-220k

Features

32,768

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ornings

-0.06

ming

-0.06

ucc

-0.06

Interfaces

-0.06

praak

-0.06

ª

-0.06

rome

-0.06

Oak

-0.06

Ã£

-0.06

enames

-0.06

POSITIVE LOGITS

ÙĪÙĨØª

0.07

atron

0.07

/Instruction

0.07

lement

0.06

AtA

0.06

vern

0.06

stoff

0.06

 wedge

0.06

weeney

0.06

Activations Density 0.018%

references to geometric directions and vectors

No Comments

No Known Activations