© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68955
    Prev
    Next
    INDEX
    Explanations

    void

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point numeric literals (decimal numbers) in code.

    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
    Produ
    -0.07
     месяцев
    -0.07
    Descri
    -0.07
    ulado
    -0.07
     समर
    -0.06
    itempty
    -0.06
     나가
    -0.06
    ありが
    -0.06
    Ion
    -0.06
     степени
    -0.06
    POSITIVE LOGITS
    Exited
    0.06
    scheme
    0.06
     Cp
    0.06
    /live
    0.06
    ToObject
    0.06
    wand
    0.06
    sub
    0.06
     whereas
    0.06
    \":\"
    0.06
    тор
    0.06
    Activations Density 0.004%

    No Known Activations