© 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. 23-RESID-POST-AA
    6. 29904
    Prev
    Next
    INDEX
    Explanations

    names

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     book
    -0.07
    VERR
    -0.06
    Encrypt
    -0.06
    District
    -0.06
     cavity
    -0.06
     outs
    -0.06
    TabIndex
    -0.06
    .page
    -0.06
    Enough
    -0.06
     kitap
    -0.06
    POSITIVE LOGITS
    �
    0.07
     моб
    0.07
     GLUT
    0.06
     Bel
    0.06
    辑
    0.06
    race
    0.06
    ۲۰۱
    0.06
     Аф
    0.06
     kW
    0.06
    _cmp
    0.06
    Activations Density 0.006%

    No Known Activations