INDEX

Explanations

law

np_max-act · gemini-2.0-flash

The neuron activates on tokens that denote legal actions or court proceedings (e.g. “sue,” “claims,” “suit,” “court,” “tort,” etc.).

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

 borne

-0.07

/↵

-0.07

_finder

-0.07

 evoke

-0.06

。。↵↵

-0.06

|.

-0.06

-inverse

-0.06

 preference

-0.06

 진행

-0.06

.md

-0.06

POSITIVE LOGITS

TextBoxColumn

0.07

_HAND

0.07

dorf

0.07

 tenía

0.07

.party

0.07

 وغير

0.07

REAL

0.06

 ries

0.06

 DevComponents

0.06

 يح

0.06

Activations Density 0.145%

law

The neuron activates on tokens that denote legal actions or court proceedings (e.g. “sue,” “claims,” “suit,” “court,” “tort,” etc.).

No Comments

No Known Activations