© 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. 15-RESID-POST-AA
    11. 108028
    Prev
    Next
    INDEX
    Explanations

    of

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    &apos
    -0.08
    unda
    -0.07
     Proceed
    -0.07
    .realpath
    -0.06
    .diag
    -0.06
    .WinControls
    -0.06
     COS
    -0.06
    +xml
    -0.06
    (金
    -0.06
     Kore
    -0.06
    POSITIVE LOGITS
     fastest
    0.07
     Affordable
    0.07
     Drawing
    0.07
    elligent
    0.07
    truncate
    0.07
    _USER
    0.06
    #%%
    0.06
     obstacle
    0.06
    Finding
    0.06
    )',↵
    0.06
    Activations Density 0.000%

    No Known Activations