© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 19-RESID-POST-AA
    11. 124749
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dickinson
    -0.07
     mentions
    -0.07
     the
    -0.07
     The
    -0.07
     Purs
    -0.07
    edor
    -0.07
     courtesy
    -0.07
     fulfill
    -0.06
     opinion
    -0.06
     Flynn
    -0.06
    POSITIVE LOGITS
     of
    0.22
     Of
    0.17
     OF
    0.17
    Of
    0.13
    -of
    0.13
    of
    0.13
    _of
    0.13
    _Of
    0.12
    	of
    0.12
     de
    0.11
    Activations Density 1.888%

    No Known Activations