© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91464
    Prev
    Next
    INDEX
    Explanations

    HTML code fragments

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens that are part of navigation menu labels (the words inside `<button>` or `<a>` elements in menus).

    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
     gear
    -0.06
     LZ
    -0.06
     compressor
    -0.06
    NSArray
    -0.06
     point
    -0.06
    ونا
    -0.06
    _rp
    -0.06
    ิศ
    -0.06
    Cog
    -0.06
    getText
    -0.06
    POSITIVE LOGITS
    글상위
    0.06
     vv
    0.06
     천
    0.06
    [keys
    0.06
     roleName
    0.06
    %).↵↵
    0.06
     dreaded
    0.06
    OCKET
    0.06
     Investigation
    0.06
     presidente
    0.06
    Activations Density 0.025%

    No Known Activations