© 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 (Instruct)
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 94043
    Prev
    Next
    INDEX
    Explanations

    strongly

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     identical
    -0.07
     Manufact
    -0.06
     domain
    -0.06
     管
    -0.06
     Native
    -0.06
     Measurement
    -0.06
     glean
    -0.06
    Brief
    -0.06
    ainers
    -0.06
     scant
    -0.06
    POSITIVE LOGITS
     strongly
    0.30
     stronghold
    0.07
    "],["
    0.06
    uencia
    0.06
     vehement
    0.06
     ")");↵
    0.06
    TypeError
    0.06
     кожного
    0.06
     Ky
    0.06
     відпов
    0.06
    Activations Density 0.003%

    No Known Activations