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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 84971
    Prev
    Next
    INDEX
    Explanations

    data analysis

    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
    ũ
    -0.07
    تور
    -0.07
     colleagues
    -0.06
    徽
    -0.06
    ERT
    -0.06
     Dispose
    -0.06
     عن
    -0.06
    ffective
    -0.06
    box
    -0.06
    Vel
    -0.06
    POSITIVE LOGITS
    _insn
    0.07
     brainstorm
    0.06
     companyId
    0.06
     ffm
    0.06
    （平成
    0.06
     tez
    0.06
     RK
    0.06
    .keep
    0.06
    FindObject
    0.06
    .angle
    0.06
    Activations Density 0.023%

    No Known Activations