© 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. 27-RESID-POST-AA
    11. 19102
    Prev
    Next
    INDEX
    Explanations

    job

    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
     mosquito
    -0.07
     terrorist
    -0.07
    enk
    -0.07
     partner
    -0.06
    Together
    -0.06
     couples
    -0.06
     Couples
    -0.06
     mayoría
    -0.06
    Markers
    -0.06
     Sure
    -0.06
    POSITIVE LOGITS
     hospodář
    0.08
    보내기
    0.08
     maxY
    0.07
     durch
    0.07
    选�
    0.07
    cpf
    0.07
    handleChange
    0.06
    ."<
    0.06
    .splice
    0.06
    shown
    0.06
    Activations Density 0.055%

    No Known Activations