© 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. 58938
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron flags floating-point numeric literals (numbers with decimal points) in code.

    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
     QName
    -0.07
     coalition
    -0.07
     pq
    -0.06
    feito
    -0.06
     :.
    -0.06
     Says
    -0.06
     consts
    -0.06
    Sand
    -0.06
    GameState
    -0.06
    Scheme
    -0.06
    POSITIVE LOGITS
     нового
    0.07
     मन
    0.06
     serbest
    0.06
    ban
    0.06
     mai
    0.06
    (return
    0.06
     pictureBox
    0.06
    과
    0.06
    engineering
    0.06
     üst
    0.06
    Activations Density 0.060%

    No Known Activations