INDEX

Explanations

body

np_max-act · gemini-2.0-flash

This neuron activates on occurrences of the word “body” (including its plural form).

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rán

-0.08

청

-0.07

 Quinn

-0.07

Queen

-0.07

 invariant

-0.07

_recent

-0.07

 Franken

-0.07

 trained

-0.07

 Alaska

-0.07

Triangle

-0.07

POSITIVE LOGITS

 Body

0.15

 body

0.14

 bodies

0.13

body

0.12

Body

0.12

 BODY

0.11

 Bodies

0.11

-body

0.11

 cuerpo

0.10

.body

0.10

Activations Density 0.044%

body

This neuron activates on occurrences of the word “body” (including its plural form).

No Comments

No Known Activations