INDEX

Explanations

Research paper citation

np_max-act · gemini-2.0-flash

The neuron detects in-text citation or reference markers (e.g. bracketed reference IDs like [@R7]).

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

 Nice

-0.06

ott

-0.06

 byste

-0.06

ょう

-0.06

皮

-0.06

Alright

-0.06

 blev

-0.06

 června

-0.06

/values

-0.05

лав

-0.05

POSITIVE LOGITS

원의

0.07

(remote

0.07

 Supporting

0.07

xdb

0.06

_LOCAL

0.06

 simpl

0.06

üçük

0.06

 kendi

0.06

xfd

0.06

Activations Density 0.009%

Research paper citation

The neuron detects in-text citation or reference markers (e.g. bracketed reference IDs like [@R7]).

No Comments

No Known Activations

Research paper citation

The neuron detects in-text citation or reference markers (e.g. bracketed reference IDs like [@R7]).

No Comments

No Known Activations