INDEX

Explanations

words relating to position, location, and visibility

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L21R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Hzfinfdu/SlimPajama-3B and open-r1/OpenR1-Math-220k

Features

32,768

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

igo

-0.10

IGO

-0.07

rad

-0.06

etas

-0.06

 fragrance

-0.06

 Origin

-0.06

 Gesch

-0.06

 sensory

-0.06

 Sticky

-0.06

POSITIVE LOGITS

 detail

0.11

/detail

0.11

 details

0.10

detail

0.10

 Detail

0.08

-detail

0.08

(detail

0.08

è¯¦æĥħ

0.08

Detail

0.08

_Detail

0.08

Activations Density 0.044%

words relating to position, location, and visibility

No Comments

No Known Activations