© 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. 15-RESID-POST-AA
    6. 125507
    Prev
    Next
    INDEX
    Explanations

    can

    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
    ROSS
    -0.09
    ross
    -0.08
    FontSize
    -0.07
     priority
    -0.06
     o
    -0.06
     Pastor
    -0.06
    �始
    -0.06
     relocate
    -0.06
    -operative
    -0.06
     lhs
    -0.06
    POSITIVE LOGITS
     can
    0.19
    can
    0.16
     Can
    0.15
     CAN
    0.14
    -can
    0.13
     could
    0.13
    Can
    0.13
    CAN
    0.13
     couldn
    0.12
    could
    0.11
    Activations Density 0.524%

    No Known Activations