© 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 (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 111785
    Prev
    Next
    INDEX
    Explanations

    提

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    creasing
    -0.06
     放
    -0.06
     Reed
    -0.06
    Value
    -0.06
    灰
    -0.06
     ped
    -0.06
     类
    -0.06
     mature
    -0.06
    Apart
    -0.06
    Escape
    -0.06
    POSITIVE LOGITS
     userDao
    0.07
    bbb
    0.07
     οικο
    0.07
     hoe
    0.06
    (to
    0.06
    ,top
    0.06
    seniz
    0.06
     کاربران
    0.06
    usaha
    0.06
     pitfalls
    0.06
    Activations Density 0.000%

    No Known Activations