© 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. 12051
    Prev
    Next
    INDEX
    Explanations

    -

    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
     penned
    -0.07
     carbonate
    -0.06
     Champions
    -0.06
    stdarg
    -0.06
    COPY
    -0.06
    variable
    -0.06
    openh
    -0.06
    _hard
    -0.06
    .springframework
    -0.06
     debated
    -0.06
    POSITIVE LOGITS
    .addButton
    0.07
     hepsi
    0.06
     uneven
    0.06
     돌아
    0.06
     mír
    0.06
    pad
    0.06
    _FOUND
    0.06
    _Port
    0.06
    _gb
    0.06
     Jewel
    0.06
    Activations Density 0.002%

    No Known Activations