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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 89138
    Prev
    Next
    INDEX
    Explanations

    that

    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
     Gingrich
    -0.07
     tiêu
    -0.07
     kredi
    -0.06
     enhances
    -0.06
    卫
    -0.06
     güvenilir
    -0.06
    238
    -0.06
    产业
    -0.05
    ablish
    -0.05
     epoxy
    -0.05
    POSITIVE LOGITS
     `,↵
    0.07
    Epoch
    0.07
    /flutter
    0.07
    .AddModelError
    0.07
     ConfigurationManager
    0.07
     persistence
    0.06
    _)
    ↵
    0.06
     somewhat
    0.06
    Transactional
    0.06
    яс
    0.06
    Activations Density 0.217%

    No Known Activations