© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 41345
    Prev
    Next
    INDEX
    Explanations

    car models

    np_max-act · gemini-2.0-flash

    This neuron fires on alphanumeric car model or chassis codes (e.g. “B8,” “S4,” “RS4,” “Mk1,” “5th generation,” etc.).

    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
     Circular
    -0.07
     않은
    -0.06
    (the
    -0.06
    assadors
    -0.06
     її
    -0.06
     Буд
    -0.06
     Marg
    -0.06
     Auswahl
    -0.06
     Ambassador
    -0.06
    Ta
    -0.06
    POSITIVE LOGITS
    strings
    0.07
    PURE
    0.06
    blast
    0.06
     concession
    0.06
     енерг
    0.06
    ])-
    0.06
     Monroe
    0.06
     prolonged
    0.06
    ποιη
    0.06
    anzi
    0.06
    Activations Density 0.010%

    No Known Activations