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. 27-RESID-POST-AA
    6. 102201
    Prev
    Next
    INDEX
    Explanations

    Southern England locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Achievement
    -0.07
     damn
    -0.07
    conference
    -0.07
    -story
    -0.07
     Tail
    -0.07
     adhesive
    -0.06
     condoms
    -0.06
    demand
    -0.06
     credit
    -0.06
     duct
    -0.06
    POSITIVE LOGITS
    बर
    0.06
     पढ़
    0.06
     obed
    0.06
    러스
    0.06
     вз
    0.06
     karar
    0.06
    GTK
    0.06
    ДК
    0.06
    วรร
    0.06
     Gtk
    0.06
    Activations Density 0.016%

    No Known Activations