© 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. 27-RESID-POST-AA
    11. 46277
    Prev
    Next
    INDEX
    Explanations

    Results of studies

    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
     Sanctuary
    -0.07
     counselling
    -0.06
     Meditation
    -0.06
     commodities
    -0.06
    violent
    -0.06
     puck
    -0.06
    Harness
    -0.06
     artworks
    -0.06
    ge
    -0.06
    โลย
    -0.06
    POSITIVE LOGITS
    -wage
    0.06
    icone
    0.06
    _tex
    0.06
    .userAgent
    0.06
     Recru
    0.06
    alnum
    0.06
     발
    0.06
    udd
    0.06
     passer
    0.06
    clist
    0.06
    Activations Density 0.035%

    No Known Activations