Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 91006
    Prev
    Next
    INDEX
    Explanations

    Trying something new

    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
    신청
    -0.08
    (geometry
    -0.07
     besch
    -0.07
     občan
    -0.06
     ceramic
    -0.06
    .enemy
    -0.06
    trace
    -0.06
     Patch
    -0.06
     trace
    -0.06
     seks
    -0.06
    POSITIVE LOGITS
     usuarios
    0.07
    "${
    0.07
    .loads
    0.06
    Manufacturer
    0.06
    ()}}↵
    0.06
    ::::/
    0.06
    xeb
    0.06
     Hindi
    0.06
     představ
    0.06
     reserved
    0.06
    Activations Density 0.004%

    No Known Activations