© 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. 7-RESID-POST-AA
    11. 8753
    Prev
    Next
    INDEX
    Explanations

    {

    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
    #----------------------------------------------------------------
    -0.07
    源
    -0.06
     Instrument
    -0.06
     briefed
    -0.06
    Adjacent
    -0.06
    บาง
    -0.06
    _initialized
    -0.06
     Slee
    -0.06
    .Popen
    -0.06
     Cameras
    -0.06
    POSITIVE LOGITS
     {(
    0.07
     moral
    0.06
     robber
    0.06
     servic
    0.06
    oldt
    0.06
    HIP
    0.06
     HIP
    0.06
     ident
    0.06
    term
    0.06
    ROADCAST
    0.06
    Activations Density 0.013%

    No Known Activations