INDEX

Explanations

like

np_max-act · gemini-2.0-flash

The neuron is triggered by occurrences of the word “like” used as a comparison or filler.

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

ึกษา

-0.07

-0.06

 đây

-0.06

FE

-0.06

 Fear

-0.06

 CLEAR

-0.06

_tl

-0.06

 However

-0.06

 nghĩ

-0.06

POSITIVE LOGITS

itesi

0.07

 Physical

0.06

Apellido

0.06

amous

0.06

ισμού

0.06

Collection

0.06

Scalar

0.06

ilage

0.06

Tet

0.06

 jobId

0.06

Activations Density 0.004%

like

The neuron is triggered by occurrences of the word “like” used as a comparison or filler.

No Comments

No Known Activations