INDEX

Explanations

Red

np_max-act · gemini-2.0-flash

This neuron detects occurrences of the substring “Red” (e.g., as the start of words like Redirection, Red Hat, Red Fly).

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

algorithm

-0.09

_fsm

-0.08

學

-0.07

.activity

-0.07

.sim

-0.07

عم

-0.07

 مطال

-0.07

/co

-0.07

loy

-0.07

	JOptionPane

-0.07

POSITIVE LOGITS

Red

0.09

 Green

0.09

ed

0.08

RED

0.08

len

0.08

 open

0.07

ED

0.07

SD

0.07

Activations Density 0.021%

Red

This neuron detects occurrences of the substring “Red” (e.g., as the start of words like Redirection, Red Hat, Red Fly).

No Comments

No Known Activations