© 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. 125126
    Prev
    Next
    INDEX
    Explanations

    portfolio

    np_max-act · gemini-2.0-flash

    The neuron activates on longer words that carry common suffixes (e.g. –ing, –ion, –ment, –ial)—essentially detecting morphologically complex terms.

    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
     ir
    -0.06
    entimes
    -0.06
    Identification
    -0.06
    (row
    -0.06
    .dark
    -0.06
     bet
    -0.06
     entonces
    -0.06
    (remove
    -0.06
    weigh
    -0.06
     Hanna
    -0.06
    POSITIVE LOGITS
    SDL
    0.07
    ौन
    0.07
    .GetCurrentMethod
    0.06
    号
    0.06
    INTERN
    0.06
    iete
    0.06
     yapıyor
    0.06
    價
    0.06
     Dysfunction
    0.06
     가능
    0.06
    Activations Density 0.192%

    No Known Activations