© 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. 55546
    Prev
    Next
    INDEX
    Explanations

    regeneration

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “regeneration” or its morphological variants (e.g. “regenerative,” “regenerating”).

    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
    襲
    -0.07
    currentUser
    -0.06
     chữ
    -0.06
     toast
    -0.06
     富
    -0.06
     emit
    -0.06
     assault
    -0.06
     bus
    -0.06
     친
    -0.06
     Katz
    -0.06
    POSITIVE LOGITS
     regeneration
    0.09
     regenerate
    0.08
    とな
    0.08
     regenerated
    0.08
    vn
    0.07
    (mysql
    0.07
    etermined
    0.07
    ITHER
    0.07
    rh
    0.07
    STEM
    0.07
    Activations Density 0.003%

    No Known Activations