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. 23-RESID-POST-AA
    6. 103962
    Prev
    Next
    INDEX
    Explanations

    Your

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ایران
    -0.06
    .connection
    -0.06
    amenti
    -0.06
     foreach
    -0.06
     defy
    -0.06
     attraction
    -0.06
     function
    -0.06
    cker
    -0.06
    utations
    -0.06
    012
    -0.06
    POSITIVE LOGITS
    lys
    0.07
    _ob
    0.07
     вку
    0.07
     ayant
    0.06
    �
    0.06
     ống
    0.06
     fatally
    0.06
    SmartyHeaderCode
    0.06
    füg
    0.06
    FindBy
    0.06
    Activations Density 0.014%

    No Known Activations