© 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. 15-RESID-POST-AA
    11. 18881
    Prev
    Next
    INDEX
    Explanations

    become

    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
     hostile
    -0.07
    -it
    -0.07
     Castillo
    -0.07
     مایل
    -0.07
    "I
    -0.07
     hasher
    -0.06
    Id
    -0.06
    (ctrl
    -0.06
     I
    -0.06
     oil
    -0.06
    POSITIVE LOGITS
     become
    0.15
     becoming
    0.15
     became
    0.14
     becomes
    0.14
     Became
    0.09
    なくな
    0.08
     Become
    0.08
    create
    0.08
    となった
    0.08
    BE
    0.08
    Activations Density 0.034%

    No Known Activations