© 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. 29830
    Prev
    Next
    INDEX
    Explanations

    Code using greater/less than

    np_max-act · gemini-2.0-flash

    The neuron never fires―it does not detect any token pattern and remains inactive on all inputs.

    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
     Yet
    -0.06
     रन
    -0.06
    GMEM
    -0.06
    (strcmp
    -0.06
    _ordered
    -0.06
     donors
    -0.06
    auction
    -0.06
     enters
    -0.06
     Simulation
    -0.06
     بيت
    -0.06
    POSITIVE LOGITS
     Deze
    0.07
     isKindOfClass
    0.07
    тал
    0.07
    보내기
    0.07
    .clientWidth
    0.06
    購
    0.06
    .datas
    0.06
    释
    0.06
     Fam
    0.06
     довольно
    0.06
    Activations Density 0.013%

    No Known Activations