© 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. 57617
    Prev
    Next
    INDEX
    Explanations

    multiple

    np_max-act · gemini-2.0-flash

    This neuron responds to parts of the text that are numeric fractions or arithmetic expressions (numbers and “/” tokens forming rational terms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
    abies
    -0.08
     Shades
    -0.06
    iore
    -0.06
    Element
    -0.06
     bisa
    -0.06
     shower
    -0.06
    MaxLength
    -0.06
     vintage
    -0.06
     newbie
    -0.06
     đứng
    -0.06
    POSITIVE LOGITS
     tys
    0.08
    /social
    0.07
     ethical
    0.06
    _;
    0.06
     fundraiser
    0.06
    datasets
    0.06
     Live
    0.06
    Emitter
    0.06
     nuôi
    0.06
     zpráva
    0.06
    Activations Density 0.001%

    No Known Activations