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

    Neuronpedia

    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. 15-RESID-POST-AA
    11. 100949
    Prev
    Next
    INDEX
    Explanations

    pornography

    np_max-act · gemini-2.0-flash

    descriptions of body parts and their physical attributes, particularly size, shape, and texture.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @grunklewordner
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    енту
    -0.06
    'en
    -0.06
     Balanced
    -0.06
    573
    -0.06
     Burn
    -0.06
     баз
    -0.06
     Eternal
    -0.06
     IST
    -0.06
    dropout
    -0.06
    ас
    -0.06
    POSITIVE LOGITS
    weit
    0.07
    .insertBefore
    0.06
    _RECE
    0.06
    应当
    0.06
    .writeFile
    0.06
    เส
    0.06
     urged
    0.06
    OCUMENT
    0.06
    ={({
    0.06
    _CHANNELS
    0.06
    Activations Density 0.064%

    No Known Activations