© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 30150
    Prev
    Next
    INDEX
    Explanations

    specific demographic characteristics and preferences related to personal profiles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itsu
    -0.07
    anja
    -0.07
    .setCode
    -0.07
    abase
    -0.07
     ArgumentException
    -0.07
    ÑĮÑİ
    -0.07
    ÙĬÙĥÙĬ
    -0.07
    ogo
    -0.07
     Wort
    -0.07
    [unit
    -0.07
    POSITIVE LOGITS
     looking
    0.06
     Seeking
    0.06
    atro
    0.06
    Seek
    0.06
    ertiary
    0.06
    ensi
    0.06
     Looking
    0.06
     matching
    0.06
     seeking
    0.06
     Giles
    0.06
    Activations Density 0.008%

    No Known Activations