© 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. 27-RESID-POST-AA
    11. 11456
    Prev
    Next
    INDEX
    Explanations

    Unproven/ineffective treatments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    podob
    -0.07
    (schedule
    -0.07
    tbody
    -0.07
    Hotel
    -0.06
    eliac
    -0.06
    Va
    -0.06
     queries
    -0.06
     rotate
    -0.06
    _tweets
    -0.06
    XE
    -0.06
    POSITIVE LOGITS
    iền
    0.07
     murderous
    0.06
     Indies
    0.06
    ole
    0.06
     Wass
    0.06
     murders
    0.06
    速
    0.06
    antaged
    0.06
    叔
    0.06
     vested
    0.06
    Activations Density 0.055%

    No Known Activations