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. 15-RESID-POST-AA
    6. 1181
    Prev
    Next
    INDEX
    Explanations

    selected

    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
    妇
    -0.07
    okt
    -0.07
    						  
    -0.07
    ánchez
    -0.06
     friday
    -0.06
    '></
    -0.06
     keine
    -0.06
    (pb
    -0.06
     Jersey
    -0.06
    79
    -0.06
    POSITIVE LOGITS
     aden
    0.07
     Kingston
    0.06
     precis
    0.06
    .le
    0.06
     regulated
    0.06
     grip
    0.06
    tan
    0.06
     gon
    0.06
     Rap
    0.06
    toUpperCase
    0.06
    Activations Density 0.030%

    No Known Activations