© 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. 14107
    Prev
    Next
    INDEX
    Explanations

    information

    np_max-act · gemini-2.0-flash

    The neuron activates on broad overview or high‐level conceptual terms (e.g. “general,” “insights,” “mechanisms,” “properties,” “trends”) that signal a summary or theoretical discussion.

    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
     Swan
    -0.07
     intimately
    -0.07
    -0.07
    _root
    -0.06
     Egyptians
    -0.06
    __.__
    -0.06
    常
    -0.06
    }'↵
    -0.06
    legacy
    -0.06
     обязательно
    -0.06
    POSITIVE LOGITS
    .xticks
    0.06
    IS
    0.06
    üc
    0.06
    eket
    0.06
     duż
    0.06
     ISC
    0.06
    (ch
    0.06
    getText
    0.06
     setResult
    0.06
    UNCT
    0.06
    Activations Density 0.048%

    No Known Activations