© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 113790
    Prev
    Next
    INDEX
    Explanations

    committed

    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
    оци
    -0.07
     Meadow
    -0.06
     ecc
    -0.06
    ?><
    -0.06
     cute
    -0.06
     rival
    -0.06
    cripts
    -0.06
    ина
    -0.06
    乙
    -0.06
     speculative
    -0.06
    POSITIVE LOGITS
    (Image
    0.07
    matplotlib
    0.06
     bundle
    0.06
    .stem
    0.06
    _NODE
    0.06
    .Volume
    0.06
     iphone
    0.06
    (xpath
    0.06
    Figure
    0.06
     Johannesburg
    0.06
    Activations Density 0.052%

    No Known Activations