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. 79978
    Prev
    Next
    INDEX
    Explanations

    end

    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
     ordinance
    -0.07
    าษ
    -0.06
     beers
    -0.06
    200
    -0.06
    EMBER
    -0.06
     restrictions
    -0.06
     audience
    -0.06
    ونة
    -0.06
    tracks
    -0.06
    series
    -0.06
    POSITIVE LOGITS
     fucked
    0.06
    окумент
    0.06
     NGOs
    0.06
    Об
    0.06
    .addTo
    0.06
    _workflow
    0.06
     กรกฎ
    0.06
    ↵  ↵
    0.06
     müssen
    0.06
     contenders
    0.06
    Activations Density 0.004%

    No Known Activations