© 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. 12975
    Prev
    Next
    INDEX
    Explanations

    quantum physics

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the scientific term “exciton” (and its close variants like “excitons” or “excitation”).

    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
     Ars
    -0.07
     jste
    -0.06
    ewhere
    -0.06
     pard
    -0.06
    若
    -0.06
    _saida
    -0.06
    RowAnimation
    -0.06
    оре
    -0.06
    .ONE
    -0.06
     Lenovo
    -0.06
    POSITIVE LOGITS
    WithTitle
    0.07
     Ton
    0.06
     grade
    0.06
     lumber
    0.06
     operator
    0.06
     Hun
    0.06
    興
    0.06
     Gren
    0.06
    Calcul
    0.06
     Del
    0.06
    Activations Density 0.002%

    No Known Activations