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. 30287
    Prev
    Next
    INDEX
    Explanations

    I

    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
    $core
    -0.07
    Scheduled
    -0.07
    $data
    -0.06
    proof
    -0.06
     sevent
    -0.06
    ”。↵↵
    -0.06
    Broad
    -0.06
     Cab
    -0.06
     Billboard
    -0.06
    _FRE
    -0.06
    POSITIVE LOGITS
     vraiment
    0.06
     autobi
    0.06
    ESTAMP
    0.06
    ionale
    0.06
    менно
    0.06
    ุบ
    0.06
     Casino
    0.06
    [...,
    0.06
    튼
    0.06
     ancora
    0.06
    Activations Density 0.040%

    No Known Activations