INDEX

Explanations

for

np_max-act · gemini-2.0-flash

The neuron fires on language naming legal claims or remedies (e.g. action, breach, damages, fraud).

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

qry

-0.08

 tvar

-0.07

Curso

-0.06

.children

-0.06

Users

-0.06

�

-0.06

 crimson

-0.06

oma

-0.06

 Cloth

-0.06

umnos

-0.06

POSITIVE LOGITS

 Progress

0.07

‌کنندگان

0.06

เพลง

0.06

-flash

0.06

.DELETE

0.06

据

0.06

ради

0.06

 Liga

0.06

Utf

0.06

目の

0.06

Activations Density 0.026%

for

The neuron fires on language naming legal claims or remedies (e.g. action, breach, damages, fraud).

No Comments

No Known Activations

for

The neuron fires on language naming legal claims or remedies (e.g. action, breach, damages, fraud).

No Comments

No Known Activations