© 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. 113235
    Prev
    Next
    INDEX
    Explanations

    code/legal 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
     Circular
    -0.07
     вод
    -0.07
     aust
    -0.06
     Mines
    -0.06
     ciddi
    -0.06
     alıp
    -0.06
     sant
    -0.06
     draining
    -0.06
     VIR
    -0.06
    reflect
    -0.06
    POSITIVE LOGITS
    DATED
    0.07
     setDefaultCloseOperation
    0.07
    _TASK
    0.07
    Autom
    0.06
    /mp
    0.06
     Bonus
    0.06
     Outs
    0.06
     fant
    0.06
    _bonus
    0.06
    。如果
    0.06
    Activations Density 0.000%

    No Known Activations