© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 127087
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up on numeric literals—especially CSS measurement values (e.g. “1.5”, “240”, “px,” etc.).

    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
     mně
    -0.06
     WWE
    -0.06
     Fakat
    -0.06
    Excel
    -0.06
    Collider
    -0.06
     キャ
    -0.06
     دوم
    -0.06
    Addr
    -0.06
     deploy
    -0.06
    Sphere
    -0.06
    POSITIVE LOGITS
    .obs
    0.07
    _RECEIVED
    0.06
     myšlen
    0.06
    -с
    0.06
     Graduate
    0.06
    pj
    0.06
    sz
    0.06
    kJ
    0.06
     Individuals
    0.06
    _pd
    0.06
    Activations Density 0.002%

    No Known Activations