© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 59109
    Prev
    Next
    INDEX
    Explanations

    phase changes and heat

    np_max-act · gemini-2.0-flash

    This neuron activates on terminology related to phase changes and latent heat (e.g., words like “latente,” “fusion,” “vaporisation,” “sublimation,” “condensation,” and “phase”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    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
     Mormons
    -0.07
     tempo
    -0.06
     Derby
    -0.06
    Apollo
    -0.06
    .ws
    -0.06
    Для
    -0.06
    aires
    -0.06
    .admin
    -0.06
    pression
    -0.06
    Place
    -0.06
    POSITIVE LOGITS
     عامة
    0.07
    OKIE
    0.07
    añ
    0.07
     harek
    0.07
     Next
    0.06
    ickt
    0.06
     vå
    0.06
    ntity
    0.06
    阳
    0.06
    ื้
    0.06
    Activations Density 0.007%

    No Known Activations