INDEX

Explanations

simple

np_max-act · gemini-2.0-flash

The neuron activates on technical descriptive adjectives or modifiers (e.g. simple, improved, miniature) used in specification‐style engineering or scientific text.

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

 playwright

-0.07

],

-0.07

 некоторых

-0.06

la

-0.06

ाजन

-0.06

 recycling

-0.06

LU

-0.06

 violates

-0.06

来

-0.06

POSITIVE LOGITS

IGINAL

0.07

ilen

0.06

MeshPro

0.06

 moss

0.06

 skins

0.06

 resend

0.06

 Easily

0.06

hex

0.06

못

0.06

(cells

0.06

Activations Density 0.144%

simple

The neuron activates on technical descriptive adjectives or modifiers (e.g. simple, improved, miniature) used in specification‐style engineering or scientific text.

No Comments

No Known Activations