INDEX

Explanations

model

np_max-act · gemini-2.0-flash

The neuron fires on self-referential disclaimers where the assistant describes itself as a “modelo de lenguaje” (e.g., “como modelo de lenguaje…”).

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

avors

-0.07

(n

-0.06

ktop

-0.06

pé

-0.06

 objective

-0.06

-ip

-0.06

natal

-0.06

(ip

-0.06

POSITIVE LOGITS

 çift

0.07

。</

0.07

gulp

0.06

 Ladies

0.06

 File

0.06

caption

0.06

 chinese

0.06

ичні

0.06

資料

0.06

）。↵

0.06

Activations Density 0.008%

model

The neuron fires on self-referential disclaimers where the assistant describes itself as a “modelo de lenguaje” (e.g., “como modelo de lenguaje…”).

No Comments

No Known Activations