INDEX

Explanations

question mark

np_max-act · gemini-2.0-flash

This neuron detects end‐of‐text or end‐of‐turn markers (e.g. the special “<|eot_id|>” token).

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

YSTICK

-0.07

 monde

-0.06

.Draw

-0.06

_adapter

-0.06

_date

-0.06

Cells

-0.06

beam

-0.06

ادن

-0.06

amics

-0.06

егодня

-0.06

POSITIVE LOGITS

�

0.07

 recreational

0.07

 diret

0.06

Orders

0.06

;$

0.06

 phòng

0.06

Authorization

0.06

Swagger

0.06

 kans

0.06

 common

0.06

Activations Density 0.037%

question mark

This neuron detects end‐of‐text or end‐of‐turn markers (e.g. the special “<|eot_id|>” token).

No Comments

No Known Activations