© 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. 15-RESID-POST-AA
    6. 73140
    Prev
    Next
    INDEX
    Explanations

    sexually explicit

    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
     activating
    -0.07
     Cay
    -0.06
    nio
    -0.06
     valley
    -0.06
     oven
    -0.06
    _PRINT
    -0.06
    agrant
    -0.06
    altet
    -0.06
     ipv
    -0.06
     yıllar
    -0.06
    POSITIVE LOGITS
     THROW
    0.08
    Just
    0.07
     شركة
    0.07
    (bottom
    0.06
    arResult
    0.06
     Hugo
    0.06
    Google
    0.06
     Hockey
    0.06
    -efficient
    0.06
     UserProfile
    0.06
    Activations Density 0.024%

    No Known Activations