© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 94739
    Prev
    Next
    INDEX
    Explanations

    story excerpts

    np_max-act · gemini-2.0-flash

    This neuron detects explicit sexual or pornographic content (often including fetishistic or violent sexual themes).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ابت
    -0.07
     efekt
    -0.07
    uria
    -0.07
     thought
    -0.07
    _circle
    -0.06
     Humph
    -0.06
     Water
    -0.06
     insisted
    -0.06
     FI
    -0.06
    :?
    -0.06
    POSITIVE LOGITS
    InnerHTML
    0.06
    "use
    0.06
    (defvar
    0.06
    들의
    0.06
    公开
    0.06
    ~~~~
    0.06
    mesini
    0.06
    _components
    0.06
     buttonWithType
    0.05
    ondo
    0.05
    Activations Density 0.065%

    No Known Activations