© 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. 90932
    Prev
    Next
    INDEX
    Explanations

    Many

    np_max-act · gemini-2.0-flash

    The neuron fires on general-purpose quantifiers and vague discourse markers (e.g. “many,” “most,” “usually,” “something”).

    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
    igate
    -0.06
     понять
    -0.06
    .stream
    -0.06
    .ge
    -0.06
     hereby
    -0.06
     quindi
    -0.06
     října
    -0.06
     trem
    -0.06
    (menu
    -0.06
     rigorous
    -0.06
    POSITIVE LOGITS
     Many
    0.08
    something
    0.07
    sparse
    0.07
     Lots
    0.07
     Last
    0.07
     Limited
    0.07
    endencies
    0.07
    Alternative
    0.07
     Doctors
    0.07
    Vý
    0.07
    Activations Density 0.090%

    No Known Activations