© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 124700
    Prev
    Next
    INDEX
    Explanations

    -cr

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find mentions of crystal structure characterization (e.g. “crystal,” “single-crystal X-ray diffraction,” “powder X-ray diffraction”).

    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
    य
    -0.07
    폐
    -0.07
     十
    -0.06
     раздел
    -0.06
    _VERTEX
    -0.06
    HELL
    -0.06
    channel
    -0.06
    velte
    -0.06
    terminal
    -0.06
    ト
    -0.06
    POSITIVE LOGITS
     dob
    0.08
     automatic
    0.07
     tốt
    0.06
    邦
    0.06
    etros
    0.06
    Sony
    0.06
     některých
    0.06
     cn
    0.06
     casts
    0.06
     cách
    0.06
    Activations Density 0.002%

    No Known Activations