© 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. 11-RESID-POST-AA
    11. 44979
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the legal parties in a case (e.g. “appellant,” “defendant,” “appellee”).

    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
     summarize
    -0.06
    ILD
    -0.06
    nam
    -0.06
    DM
    -0.06
    (Connection
    -0.06
    دا
    -0.06
     chiế
    -0.06
     alguns
    -0.06
     install
    -0.06
     select
    -0.06
    POSITIVE LOGITS
    requency
    0.06
     quyền
    0.06
    ées
    0.06
    .readyState
    0.06
    _verification
    0.06
    _TX
    0.05
     incap
    0.05
    Sharp
    0.05
    (Direction
    0.05
     тяж
    0.05
    Activations Density 0.004%

    No Known Activations