© 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. 38053
    Prev
    Next
    INDEX
    Explanations

    Search queries/text snippets

    np_max-act · gemini-2.0-flash

    This neuron detects user requests for instructions or encouragement to engage in harmful or illegal actions (including self-harm).

    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
    posted
    -0.07
     Bless
    -0.06
     사무
    -0.06
    ν
    -0.06
     نفر
    -0.06
     यद
    -0.06
    flowers
    -0.06
    vector
    -0.06
     illicit
    -0.06
    净
    -0.06
    POSITIVE LOGITS
     multid
    0.07
    (resultado
    0.07
     geliştir
    0.07
     phủ
    0.07
     Václav
    0.06
    CERT
    0.06
     mism
    0.06
    _pll
    0.06
     kendisini
    0.06
    _INF
    0.06
    Activations Density 0.012%

    No Known Activations