© 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. 27-RESID-POST-AA
    11. 93322
    Prev
    Next
    INDEX
    Explanations

    margin

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enc
    -0.07
    connections
    -0.07
    _words
    -0.07
    /example
    -0.07
     pizza
    -0.07
    target
    -0.07
    .partial
    -0.07
     ink
    -0.07
    timing
    -0.07
    紙
    -0.07
    POSITIVE LOGITS
     αρ
    0.06
     analytics
    0.06
     avere
    0.06
    変わ
    0.06
    liğ
    0.06
    Tyler
    0.06
    (hwnd
    0.06
     DirectX
    0.06
    _EL
    0.06
     leh
    0.06
    Activations Density 0.021%

    No Known Activations