© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RESID-POST-AA
    11. 46474
    Prev
    Next
    INDEX
    Explanations

    French titles/names

    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
    qtt
    -0.08
    goo
    -0.07
    иболее
    -0.07
     Roots
    -0.07
     الش
    -0.07
     TCHAR
    -0.07
    Winner
    -0.06
    ViewPager
    -0.06
     intimidating
    -0.06
     Communist
    -0.06
    POSITIVE LOGITS
     sir
    0.09
    .change
    0.06
     mr
    0.06
    SECTION
    0.06
    amacare
    0.06
     Ис
    0.06
    quivo
    0.06
     разом
    0.06
    isl
    0.05
    own
    0.05
    Activations Density 0.023%

    No Known Activations