© 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. 54157
    Prev
    Next
    INDEX
    Explanations

    protein/receptor molecules

    np_max-act · gemini-2.0-flash

    This neuron activates on uppercase alphanumeric strings that look like gene or protein identifiers (e.g. “CUL1,” “RBX1,” “NAE1,” “UBE2F”).

    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
    _pan
    -0.07
     společně
    -0.07
     bouquet
    -0.07
     Lawson
    -0.07
     трохи
    -0.06
     Basel
    -0.06
     %>
    -0.06
     четы
    -0.06
     Barr
    -0.06
     (>
    -0.06
    POSITIVE LOGITS
     furnished
    0.07
     ########.
    0.07
    都
    0.07
     článku
    0.06
     springs
    0.06
     lẽ
    0.06
    .......
    0.06
     Sonic
    0.06
     propel
    0.06
    StateToProps
    0.06
    Activations Density 0.047%

    No Known Activations