INDEX

Explanations

First-person pronouns

np_max-act · gemini-2.0-flash

references to time periods and significant historical events.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

the neuron's main cue is first-person narrator language—tokens that indicate the author speaking about their own actions, thoughts, or experiences (I, we, my, etc.).

oai_token-act-pair · gpt-5-mini Triggered by @vetterc0

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

-0.07

env

-0.07

Add

-0.07

,st

-0.07

contexts

-0.06

/exp

-0.06

.export

-0.06

凝

-0.06

販売

-0.06

icom

-0.06

POSITIVE LOGITS

'].'</

0.07

0.06

 lies

0.06

 multiply

0.06

.What

0.06

 составляет

0.06

şu

0.06

GHC

0.06

 Starts

0.06

 anything

0.06

Activations Density 0.341%

First-person pronouns

references to time periods and significant historical events.

the neuron's main cue is first-person narrator language—tokens that indicate the author speaking about their own actions, thoughts, or experiences (I, we, my, etc.).

No Comments

No Known Activations

First-person pronouns

references to time periods and significant historical events.

the neuron's main cue is first-person narrator language—tokens that indicate the author speaking about their own actions, thoughts, or experiences (I, we, my, etc.).

No Comments

No Known Activations