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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126600
    Prev
    Next
    INDEX
    Explanations

    smooth

    np_max-act · gemini-2.0-flash

    statements related to the classification and properties of complex varieties and manifolds in algebraic geometry.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on technical mathematical descriptors—especially adjectives like “smooth,” “singular,” and “generic” used to qualify geometric objects.

    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
    uction
    -0.07
     mắt
    -0.07
     mirrors
    -0.06
     born
    -0.06
    計算
    -0.06
     Urdu
    -0.06
     ces
    -0.06
     ali
    -0.06
    搬
    -0.06
     Thesis
    -0.06
    POSITIVE LOGITS
     영상
    0.06
    (mysql
    0.06
    erli
    0.06
    PLOY
    0.06
    isma
    0.06
    ються
    0.06
     Roz
    0.05
    colors
    0.05
     GridBagConstraints
    0.05
    瑞
    0.05
    Activations Density 0.001%

    No Known Activations