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. 31679
    Prev
    Next
    INDEX
    Explanations

    ductor

    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
    .She
    -0.06
     原
    -0.06
     Caul
    -0.06
     hereby
    -0.06
     pitfalls
    -0.06
    Pow
    -0.06
    .And
    -0.06
     reint
    -0.06
    .Restrict
    -0.06
     mediums
    -0.06
    POSITIVE LOGITS
     materi
    0.07
    ไข
    0.07
    <Key
    0.07
     UInt
    0.07
    иплом
    0.07
    /client
    0.06
    _OID
    0.06
     Κου
    0.06
     bout
    0.06
    이스
    0.06
    Activations Density 0.105%

    No Known Activations