Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 129262
    Prev
    Next
    INDEX
    Explanations

    biological/chemical response

    np_max-act · gemini-2.0-flash

    The neuron is selectively identifying technical phase or component descriptors (e.g. “initial,” “basic,” “tonic,” “prolonged,” “component”) used to describe stages of a physiological 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
    plugin
    -0.07
    ワ
    -0.07
    Shipping
    -0.07
     Geb
    -0.06
     Shipping
    -0.06
    _skip
    -0.06
     Vul
    -0.06
    "One
    -0.06
     Chad
    -0.06
     MMI
    -0.06
    POSITIVE LOGITS
    .pivot
    0.08
    Hola
    0.07
    ดา
    0.06
     �
    0.06
    acerb
    0.06
    >true
    0.06
    _FLOAT
    0.06
     :=↵
    0.06
     sánh
    0.06
    -dev
    0.06
    Activations Density 0.020%

    No Known Activations