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. 129358
    Prev
    Next
    INDEX
    Explanations

    discrimination and harassment

    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
     tougher
    -0.07
     MessageLookup
    -0.07
     findOne
    -0.06
    Parcelable
    -0.06
    によ
    -0.06
     Základní
    -0.06
     않
    -0.06
    真正
    -0.06
    كية
    -0.06
    mant
    -0.06
    POSITIVE LOGITS
    -fashion
    0.07
     nisi
    0.06
    elligence
    0.06
    /change
    0.06
     адміністра
    0.06
    alez
    0.06
    ø
    0.06
     Satellite
    0.06
     ultrasound
    0.06
    .off
    0.06
    Activations Density 0.071%

    No Known Activations