INDEX

Explanations

ality

np_max-act · gemini-2.0-flash

The neuron detects occurrences of the word “modality” (and its plural “modalities”).

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

ेक

-0.06

nep

-0.06

 канди

-0.06

	StringBuilder

-0.06

 kvůli

-0.06

 near

-0.06

 nebude

-0.06

 Brief

-0.06

Uk

-0.06

 creek

-0.06

POSITIVE LOGITS

 mode

0.08

Protocol

0.08

 modal

0.08

 modes

0.08

 Protocol

0.08

 Mode

0.07

Lux

0.07

odal

0.07

tabs

0.07

омет

0.07

Activations Density 0.005%

ality

The neuron detects occurrences of the word “modality” (and its plural “modalities”).

No Comments

No Known Activations

ality

The neuron detects occurrences of the word “modality” (and its plural “modalities”).

No Comments

No Known Activations