© 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. 11-RESID-POST-AA
    6. 49937
    Prev
    Next
    INDEX
    Explanations

    is

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $c
    -0.06
    _REGISTRY
    -0.06
    Baseline
    -0.06
     muj
    -0.06
     captain
    -0.06
     Gry
    -0.06
    Modal
    -0.06
     belonging
    -0.06
     email
    -0.06
    Node
    -0.06
    POSITIVE LOGITS
     FirebaseAuth
    0.07
    .Right
    0.07
    ßerdem
    0.06
     peníze
    0.06
    .listeners
    0.06
     lanz
    0.06
     yayım
    0.06
     texture
    0.06
    .addEventListener
    0.06
     zpět
    0.06
    Activations Density 0.009%

    No Known Activations