© 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. 7-RESID-POST-AA
    6. 9973
    Prev
    Next
    INDEX
    Explanations

    proportions/ratios/shares

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blond
    -0.07
    Auth
    -0.07
    _yaw
    -0.07
    ISION
    -0.06
     vue
    -0.06
    old
    -0.06
    ereotype
    -0.06
     куда
    -0.06
     dinner
    -0.06
     reality
    -0.06
    POSITIVE LOGITS
     fn
    0.07
     supremacy
    0.07
     PURE
    0.07
    _terminal
    0.06
     promotes
    0.06
    RSA
    0.06
    	fn
    0.06
    sw
    0.06
    ilenames
    0.06
    _related
    0.06
    Activations Density 0.209%

    No Known Activations