© 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. 11-RESID-POST-AA
    11. 51391
    Prev
    Next
    INDEX
    Explanations

    Verbs describing actions/states

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fü
    -0.07
     변화
    -0.07
    Eval
    -0.07
     dese
    -0.07
    willReturn
    -0.07
    -ar
    -0.06
    งเศส
    -0.06
     habitual
    -0.06
     jednodu
    -0.06
    817
    -0.06
    POSITIVE LOGITS
     fucks
    0.06
    .guid
    0.06
     starring
    0.06
     examined
    0.06
    screens
    0.06
    cop
    0.06
    -то
    0.06
     FUCK
    0.06
    _TR
    0.06
     Carolina
    0.06
    Activations Density 0.370%

    No Known Activations