INDEX

Explanations

ide

np_max-act · gemini-2.0-flash

This neuron activates primarily on mentions of hydrogen sulfide (H₂S) and related chemical terminology.

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

ому

-0.07

/YYYY

-0.07

Row

-0.06

 Scrap

-0.06

 acknow

-0.06

 Yüksek

-0.06

Wor

-0.06

edx

-0.06

 restroom

-0.06

Cells

-0.06

POSITIVE LOGITS

 assigning

0.07

 refining

0.07

worksheet

0.06

řich

0.06

 anticipate

0.06

 extend

0.06

 documentation

0.06

(priv

0.06

 within

0.06

 affect

0.06

Activations Density 0.007%

ide

This neuron activates primarily on mentions of hydrogen sulfide (H₂S) and related chemical terminology.

No Comments

No Known Activations