© 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. 116716
    Prev
    Next
    INDEX
    Explanations

    a

    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
    θλη
    -0.07
    _THREAD
    -0.07
     التاريخ
    -0.07
     ภาษ
    -0.07
     respecto
    -0.07
     meille
    -0.07
     الهند
    -0.07
     Ελλάδα
    -0.07
    _stock
    -0.06
     siti
    -0.06
    POSITIVE LOGITS
     a
    0.34
     A
    0.25
     an
    0.24
    A
    0.21
    a
    0.17
     An
    0.16
    -a
    0.16
    .A
    0.16
    An
    0.16
     A
    0.16
    Activations Density 1.851%

    No Known Activations