© 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. 44242
    Prev
    Next
    INDEX
    Explanations

    area

    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
    flation
    -0.07
    уванням
    -0.06
     collects
    -0.06
    應
    -0.06
     confidence
    -0.06
    filesize
    -0.06
    ются
    -0.06
    abajo
    -0.06
    595
    -0.06
    Persist
    -0.05
    POSITIVE LOGITS
    ()>
    0.07
    NOP
    0.06
    -T
    0.06
     Fiat
    0.06
     __
    0.06
    nome
    0.06
     조금
    0.06
     �
    0.06
    <head
    0.06
     Anatomy
    0.06
    Activations Density 0.013%

    No Known Activations