© 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 EvalsExportsAPI 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. 56503
    Prev
    Next
    INDEX
    Explanations

    Damaging past revealed

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of online or digital media content (e.g. photos, videos, social‐media posts).

    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
    (Photo
    -0.06
    :]:↵
    -0.06
    xiv
    -0.06
    BuildContext
    -0.06
    "With
    -0.06
    不知
    -0.06
    ились
    -0.06
     между
    -0.06
    Finder
    -0.06
     cumshot
    -0.06
    POSITIVE LOGITS
    .Max
    0.07
    uffled
    0.07
    .fits
    0.06
     čas
    0.06
     influenza
    0.06
     Paige
    0.06
    _AES
    0.06
    criptor
    0.06
     jugador
    0.06
    unny
    0.06
    Activations Density 0.036%

    No Known Activations