© 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. 11-RESID-POST-AA
    6. 24709
    Prev
    Next
    INDEX
    Explanations

    Return on investment

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    footer
    -0.07
    �
    -0.06
     дво
    -0.06
     vocals
    -0.06
    --------------------------------
    -0.06
     straps
    -0.06
    opr
    -0.06
     nude
    -0.06
     requirement
    -0.06
     --------------------------------
    -0.06
    POSITIVE LOGITS
     نتیجه
    0.07
     fruition
    0.07
    oenix
    0.07
     Acc
    0.07
     Camb
    0.06
     Decom
    0.06
     Illuminate
    0.06
     Ag
    0.06
    Ac
    0.06
    ,event
    0.06
    Activations Density 0.010%

    No Known Activations