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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 73974
    Prev
    Next
    INDEX
    Explanations

    code

    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
    -parent
    -0.07
     Press
    -0.07
     Theater
    -0.06
     дер
    -0.06
    	bs
    -0.06
    olf
    -0.06
    _fore
    -0.06
    emplates
    -0.05
     Wochen
    -0.05
     nen
    -0.05
    POSITIVE LOGITS
     })(
    0.07
     UIAlertView
    0.07
    _subs
    0.06
     inputValue
    0.06
    aman
    0.06
    ์เพ
    0.06
     constexpr
    0.06
    -O
    0.06
     unn
    0.06
    Popup
    0.06
    Activations Density 0.002%

    No Known Activations