© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 76021
    Prev
    Next
    INDEX
    Explanations

    academic 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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipzig
    -0.06
    	answer
    -0.06
     Mount
    -0.06
    .SuspendLayout
    -0.06
    affer
    -0.06
    Blue
    -0.06
     كور
    -0.06
     cones
    -0.05
    allee
    -0.05
     plugs
    -0.05
    POSITIVE LOGITS
    -of
    0.08
    -To
    0.08
    _GO
    0.07
    -in
    0.07
     Heg
    0.07
    ريقة
    0.07
    -by
    0.07
    -In
    0.07
    -on
    0.07
    cth
    0.07
    Activations Density 0.020%

    No Known Activations