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. 11-RESID-POST-AA
    6. 123622
    Prev
    Next
    INDEX
    Explanations

    name

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (handle
    -0.07
     zus
    -0.07
     Роз
    -0.06
    ats
    -0.06
     Democrat
    -0.06
     kal
    -0.06
    (is
    -0.06
    Wake
    -0.06
    弘
    -0.06
    reinterpret
    -0.06
    POSITIVE LOGITS
    。↵
    0.07
    ]);↵
    0.07
     )↵
    0.06
    )↵
    0.06
    paused
    0.06
    。
    0.06
    )])↵
    0.06
     Property
    0.06
    ،↵
    0.06
    .↵
    0.06
    Activations Density 0.024%

    No Known Activations