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. 94929
    Prev
    Next
    INDEX
    Explanations

    .get

    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
    вест
    -0.08
    ικού
    -0.06
    ود
    -0.06
     Marino
    -0.06
     Bend
    -0.06
     loa
    -0.06
     paging
    -0.06
    UNG
    -0.06
    .plist
    -0.06
     Merchant
    -0.06
    POSITIVE LOGITS
    worksheet
    0.07
    .Alert
    0.07
    _Syntax
    0.06
    очный
    0.06
    tility
    0.06
    Trad
    0.06
     vows
    0.06
     Apprec
    0.06
     ARISING
    0.06
    _LED
    0.06
    Activations Density 0.014%

    No Known Activations