© 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. 73660
    Prev
    Next
    INDEX
    Explanations

    growth and increase

    np_max-act · gemini-2.0-flash

    content related to biological processes and physiological responses in experimental studies.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on numerical measurements and their changes (e.g., rising power readings and steady‐state values over time).

    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
    (calendar
    -0.07
     helps
    -0.07
     컴
    -0.07
    excel
    -0.07
    нок
    -0.06
     weak
    -0.06
    ügen
    -0.06
    .Word
    -0.06
     Achievement
    -0.06
    524
    -0.06
    POSITIVE LOGITS
    _neighbor
    0.06
     destined
    0.06
     professionnel
    0.06
    ("");
    ↵
    0.06
     INSTANCE
    0.06
     Graph
    0.06
     progressively
    0.06
    Concrete
    0.06
     вод
    0.05
     Παρ
    0.05
    Activations Density 0.164%

    No Known Activations