© 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. 15-RESID-POST-AA
    6. 107016
    Prev
    Next
    INDEX
    Explanations

    definitions of terms

    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
    αιν
    -0.07
    orce
    -0.07
    rollers
    -0.06
    type
    -0.06
     א
    -0.06
    ум
    -0.06
     prest
    -0.06
    ilece
    -0.06
    joint
    -0.06
    .node
    -0.06
    POSITIVE LOGITS
     Circ
    0.06
    TOR
    0.06
     CID
    0.06
    gger
    0.06
    说的
    0.06
    sphere
    0.06
     vocational
    0.06
     Carnival
    0.06
     penetrate
    0.06
    _POL
    0.06
    Activations Density 0.045%

    No Known Activations