© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59162
    Prev
    Next
    INDEX
    Explanations

    Code, commands

    np_max-act · gemini-2.0-flash

    The neuron spotlights occurrences of the “-U” flag in pacman commands (i.e. the pacman -U install/upgrade syntax).

    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
     santa
    -0.07
    ادث
    -0.06
    manın
    -0.06
     Builders
    -0.06
    _fragment
    -0.06
    -foot
    -0.06
    -last
    -0.06
     Obama
    -0.06
     Lower
    -0.06
     MST
    -0.06
    POSITIVE LOGITS
     getElement
    0.07
     Experiment
    0.07
    lescope
    0.07
    .handleSubmit
    0.07
    Experiment
    0.07
    getUser
    0.07
     talks
    0.07
    poi
    0.07
     register
    0.07
    SW
    0.07
    Activations Density 0.048%

    No Known Activations