© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92138
    Prev
    Next
    INDEX
    Explanations

    have

    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
    مة
    -0.07
    자료
    -0.07
    数据
    -0.07
    ypo
    -0.06
    běh
    -0.06
    Solar
    -0.06
     observed
    -0.06
     Shows
    -0.06
     Fs
    -0.06
    是个
    -0.06
    POSITIVE LOGITS
    adjust
    0.07
    ],[
    0.07
     getIntent
    0.07
     Inspiration
    0.06
    liği
    0.06
    _Offset
    0.06
    uniq
    0.06
    :start
    0.06
     가능한
    0.06
    .addEventListener
    0.06
    Activations Density 0.013%

    No Known Activations