© 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. 114164
    Prev
    Next
    INDEX
    Explanations

    general text

    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
     równ
    -0.09
    <r
    -0.06
    ้าย
    -0.06
    asin
    -0.06
    $q
    -0.06
    IMIT
    -0.06
    说话
    -0.05
    inces
    -0.05
    发行
    -0.05
    #
    -0.05
    POSITIVE LOGITS
     inspection
    0.07
     interpolate
    0.07
    (currentUser
    0.07
    _PADDING
    0.07
     inspections
    0.07
    =https
    0.07
    _LOGIN
    0.07
    MD
    0.07
     Encode
    0.07
     провед
    0.07
    Activations Density 0.000%

    No Known Activations