© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RESID-POST-AA
    11. 58198
    Prev
    Next
    INDEX
    Explanations

    sex

    np_max-act · gemini-2.0-flash

    The neuron activates on explicit sexual or erotic terms indicating pornography or sexual content.

    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
    وپ
    -0.07
     Eduardo
    -0.06
    wal
    -0.06
    -ps
    -0.06
     Ο
    -0.06
     metavar
    -0.06
     ">
    -0.06
    td
    -0.06
    hPa
    -0.06
    WARN
    -0.05
    POSITIVE LOGITS
    .beans
    0.07
    Their
    0.07
     perceive
    0.07
     Uluslararası
    0.07
    RequestBody
    0.06
    就会
    0.06
    iggins
    0.06
    ................................
    0.06
     marginLeft
    0.06
    ---↵↵
    0.06
    Activations Density 0.079%

    No Known Activations