© 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. 56912
    Prev
    Next
    INDEX
    Explanations

    predict

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect words and phrases expressing prediction or predictive risk (e.g. “predict,” “predictor,” “identify [as risk],” “risk factor”).

    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
    پس
    -0.07
    plugins
    -0.07
    _press
    -0.06
    IsActive
    -0.06
    rength
    -0.06
     时间
    -0.06
    ��
    -0.06
     Transparency
    -0.06
     onchange
    -0.06
    ADDR
    -0.06
    POSITIVE LOGITS
     fundament
    0.07
     Indicates
    0.07
     principal
    0.07
     canine
    0.06
     veriler
    0.06
     wholes
    0.06
     cart
    0.06
     Indies
    0.06
    รายการ
    0.06
    est
    0.06
    Activations Density 0.013%

    No Known Activations