INDEX

Explanations

shadow

np_max-act · gemini-2.0-flash

texts pertaining to the history of science.

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

The neuron detects self-referential mentions of “writing” or “story” (i.e. meta references to authorship or narrative).

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

_freq

-0.06

 культуры

-0.06

 leftist

-0.06

ูกค

-0.06

 addUser

-0.06

 bạc

-0.06

 Nelson

-0.06

Am

-0.06

 forn

-0.06

仰

-0.06

POSITIVE LOGITS

 />)↵

0.07

 succes

0.06

골

0.06

στε

0.06

qed

0.06

FormControl

0.06

 Resize

0.06

nonce

0.06

 totalmente

0.06

์และ

0.06

Activations Density 0.426%

shadow

texts pertaining to the history of science.

The neuron detects self-referential mentions of “writing” or “story” (i.e. meta references to authorship or narrative).

No Comments

No Known Activations