© 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. 55585
    Prev
    Next
    INDEX
    Explanations

    CSS styling

    np_max-act · gemini-2.0-flash

    The neuron fires on the beginnings of CSS rules, i.e. selector tokens that introduce a `{` block.

    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
     Wholesale
    -0.07
     pb
    -0.07
    ानत
    -0.07
    ,buf
    -0.07
    ště
    -0.07
    _Texture
    -0.07
    GitHub
    -0.06
     Pill
    -0.06
    ivan
    -0.06
     Penis
    -0.06
    POSITIVE LOGITS
    irect
    0.06
    经营
    0.06
     Cuba
    0.06
     خواست
    0.06
     dred
    0.06
    lux
    0.05
    .”↵↵
    0.05
     attempt
    0.05
    ยวก
    0.05
     Ан
    0.05
    Activations Density 0.001%

    No Known Activations