Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 125821
    Prev
    Next
    INDEX
    Explanations

    pornography

    np_max-act · gemini-2.0-flash

    This neuron detects explicit sexual content terminology (e.g., porn-related words).

    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
    _cmds
    -0.07
    Milliseconds
    -0.07
     kW
    -0.07
     menus
    -0.06
    _pk
    -0.06
     Některá
    -0.06
    blood
    -0.06
    jango
    -0.06
    -Sah
    -0.06
    冒
    -0.06
    POSITIVE LOGITS
     zg
    0.07
     prés
    0.06
     abusing
    0.06
     credit
    0.06
     worksheet
    0.06
    _Pre
    0.06
     dán
    0.06
     ({↵
    0.06
    .reject
    0.06
    ".$
    0.06
    Activations Density 0.032%

    No Known Activations