© 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. 55898
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron reliably activates on content‐heavy, domain-specific nouns that denote key biological or experimental processes/outcomes (e.g. “performance,” “function,” “cycles,” “expenditure,” “formation,” “exocytosis,” “response”).

    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
    ,id
    -0.07
    电视
    -0.06
    _plus
    -0.06
    電視
    -0.06
    +E
    -0.06
    guards
    -0.06
     Razor
    -0.06
     society
    -0.06
    _Printf
    -0.06
    Probe
    -0.06
    POSITIVE LOGITS
     případě
    0.07
    urent
    0.07
    스를
    0.07
    いか
    0.06
    (pin
    0.06
    .person
    0.06
     quando
    0.06
    (encoding
    0.06
    _lex
    0.06
     материала
    0.06
    Activations Density 0.047%

    No Known Activations