© 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. 885
    Prev
    Next
    INDEX
    Explanations

    erotic themes

    np_max-act · gemini-2.0-flash

    The neuron is detecting mentions of permission or authorization language, particularly around granting or withholding permission to climax.

    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
    َ
    -0.07
     nipples
    -0.06
    home
    -0.06
     ascii
    -0.06
    不同的
    -0.06
     barber
    -0.06
    ุณ
    -0.06
    Untitled
    -0.06
    агато
    -0.06
    iro
    -0.06
    POSITIVE LOGITS
    ::|
    0.06
    tbl
    0.06
    );}↵
    0.06
     كور
    0.06
    -categories
    0.06
    hasil
    0.06
    _ml
    0.06
    Weapons
    0.06
     используют
    0.06
    fono
    0.06
    Activations Density 0.007%

    No Known Activations