© 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
    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. 56077
    Prev
    Next
    INDEX
    Explanations

    doing tasks

    np_max-act · gemini-2.0-flash

    The neuron fires on language that expresses ability or permission—e.g. modal and capability words like “can,” “could,” “do,” “anything,” and “direct.”

    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
    Statics
    -0.07
    นเต
    -0.06
    زد
    -0.06
     imposed
    -0.06
    loy
    -0.06
     αφ
    -0.06
    -beta
    -0.06
    /tests
    -0.05
    #plt
    -0.05
    कन
    -0.05
    POSITIVE LOGITS
     rz
    0.07
     sedan
    0.07
     Pain
    0.06
     watchers
    0.06
     потол
    0.06
    recent
    0.06
     Claude
    0.06
    国際
    0.06
    abler
    0.06
     Дж
    0.06
    Activations Density 0.006%

    No Known Activations