INDEX

Explanations

this

np_max-act · gemini-2.0-flash

The neuron detects terminology related to legal disputes—mentions of lawsuits, suing, arrests, legal action, and related courtroom or litigation language.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

drag

-0.07

_ste

-0.07

Sarah

-0.07

Magic

-0.06

Qual

-0.06

controllers

-0.06

 Workplace

-0.06

 proud

-0.06

brıs

-0.06

shader

-0.06

POSITIVE LOGITS

'><

0.07

literal

0.07

={}↵

0.07

[in

0.07

 charset

0.07

 opacity

0.06

نگی

0.06

(Unit

0.06

lod

0.06

($_

0.06

Activations Density 0.094%

this

The neuron detects terminology related to legal disputes—mentions of lawsuits, suing, arrests, legal action, and related courtroom or litigation language.

No Comments

No Known Activations