© 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. 15-RESID-POST-AA
    6. 10849
    Prev
    Next
    INDEX
    Explanations

    3

    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
     pě
    -0.06
    .lb
    -0.06
     McMahon
    -0.06
     journeys
    -0.06
     statistics
    -0.06
     rsa
    -0.06
     घर
    -0.06
     عملی
    -0.06
    .da
    -0.06
     specs
    -0.06
    POSITIVE LOGITS
    rganization
    0.08
     Appalach
    0.07
    buff
    0.07
    orbit
    0.07
     "");
    0.06
    (for
    0.06
    structures
    0.06
    getView
    0.06
    =this
    0.06
    Cors
    0.06
    Activations Density 0.011%

    No Known Activations