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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 110688
    Prev
    Next
    INDEX
    Explanations

    advice

    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
     abolition
    -0.07
    Spy
    -0.06
    _even
    -0.06
    apeutic
    -0.06
     merit
    -0.06
    рина
    -0.06
    Danger
    -0.06
     undocumented
    -0.06
    .minutes
    -0.06
     Rabbit
    -0.06
    POSITIVE LOGITS
    (cancel
    0.08
    ât
    0.08
    ="(
    0.07
     Bf
    0.07
     OMAP
    0.07
    (od
    0.07
     dří
    0.06
    спіль
    0.06
     UIManager
    0.06
    ionales
    0.06
    Activations Density 0.103%

    No Known Activations