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. 15-RESID-POST-AA
    6. 12045
    Prev
    Next
    INDEX
    Explanations

    the

    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
    とう
    -0.07
    WARN
    -0.07
     لكرة
    -0.07
    HDATA
    -0.06
     chtěl
    -0.06
    كر
    -0.06
    天天
    -0.06
    ��
    -0.06
    уванні
    -0.06
    言わ
    -0.06
    POSITIVE LOGITS
     efficacy
    0.06
     Disabilities
    0.06
     reclaimed
    0.06
     Shed
    0.06
     вес
    0.06
     Apostle
    0.06
    _<
    0.06
    ens
    0.06
     Massachusetts
    0.06
    reed
    0.05
    Activations Density 0.001%

    No Known Activations