INDEX

Explanations

(

np_max-act · gemini-2.0-flash

This neuron activates on stack‐trace lines (the “at Module…”, file path, and line/column references) in error logs.

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

division

-0.07

quote

-0.07

 root

-0.07

mv

-0.07

 flavours

-0.07

scribe

-0.06

 namely

-0.06

 دانشجوی

-0.06

,color

-0.06

 command

-0.06

POSITIVE LOGITS

@Enable

0.06

 سو

0.06

の上

0.06

�

0.06

 đặc

0.06

 Bound

0.06

 otom

0.06

 contempt

0.05

 essa

0.05

 thưởng

0.05

Activations Density 0.001%

(

This neuron activates on stack‐trace lines (the “at Module…”, file path, and line/column references) in error logs.

No Comments

No Known Activations