© 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. 20860
    Prev
    Next
    INDEX
    Explanations

    of

    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
     چند
    -0.08
    belongs
    -0.06
    lá
    -0.06
     کم
    -0.06
     cavern
    -0.06
     쓰
    -0.06
     우
    -0.06
     fulfil
    -0.06
    _eof
    -0.06
    !!!!!!!!
    -0.06
    POSITIVE LOGITS
    ynchronize
    0.07
    RYPT
    0.06
    режд
    0.06
    .RequestMethod
    0.06
    /editor
    0.06
    regs
    0.06
    OPSIS
    0.06
     прид
    0.06
     kitty
    0.06
    hp
    0.06
    Activations Density 0.011%

    No Known Activations