© 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. 7-RESID-POST-AA
    11. 94007
    Prev
    Next
    INDEX
    Explanations

    social media posts

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    The
    -0.07
     Fet
    -0.06
     encoder
    -0.06
    ��
    -0.06
     ancestral
    -0.06
    .↵
    -0.06
    όρ
    -0.06
     blah
    -0.06
    青年
    -0.06
     ошиб
    -0.06
    POSITIVE LOGITS
     anytime
    0.06
     Ob
    0.06
    Growing
    0.06
     payoff
    0.06
     invites
    0.06
     discipline
    0.06
     jurors
    0.06
     Drive
    0.06
     hearings
    0.06
    ?',
    0.05
    Activations Density 0.110%

    No Known Activations