Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 30152
    Prev
    Next
    INDEX
    Explanations

    name

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Дж
    -0.06
     tossed
    -0.06
     Pastor
    -0.06
     trop
    -0.06
     Nx
    -0.06
    とする
    -0.06
    Unlock
    -0.06
    Jac
    -0.06
    iming
    -0.06
    と思う
    -0.06
    POSITIVE LOGITS
    (firstName
    0.07
    ascript
    0.06
     interle
    0.06
     csrf
    0.06
    -names
    0.06
     named
    0.06
     exit
    0.06
     microscope
    0.06
     humanity
    0.06
    anel
    0.06
    Activations Density 0.002%

    No Known Activations