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. 7100
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
    letes
    -0.07
     polys
    -0.07
     частина
    -0.07
    かの
    -0.07
    _roll
    -0.07
     Knox
    -0.07
    ducible
    -0.06
     آل
    -0.06
     Bazı
    -0.06
     Contacts
    -0.06
    POSITIVE LOGITS
    _DECL
    0.07
    严
    0.06
    盛
    0.06
    ΟΥΣ
    0.06
    _prompt
    0.06
    *p
    0.06
    ").↵
    0.06
    ecd
    0.06
     ΑΝ
    0.06
    _CLASSES
    0.06
    Activations Density 0.074%

    No Known Activations