© 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. 54140
    Prev
    Next
    INDEX
    Explanations

    Unicode

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on technical character‐encoding terminology—e.g. names of encodings or standards (like “Unicode,” “ISO/IEC,” “encoder,” “UCS”).

    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
     withdrawal
    -0.07
    ємо
    -0.07
     unspecified
    -0.06
    .dist
    -0.06
    results
    -0.06
     imm
    -0.06
    estimate
    -0.06
     wind
    -0.06
     consumo
    -0.06
     reun
    -0.06
    POSITIVE LOGITS
     мот
    0.07
     Май
    0.07
     проф
    0.06
    Conv
    0.06
    .VisualBasic
    0.06
     Asp
    0.06
     accompl
    0.06
     ForeignKey
    0.06
    _pol
    0.06
     مو
    0.06
    Activations Density 0.003%

    No Known Activations