© 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. 72383
    Prev
    Next
    INDEX
    Explanations

    terms related to online advertising and marketing strategies

    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
     Knox
    -0.07
    iso
    -0.07
    save
    -0.06
     save
    -0.06
    ocator
    -0.06
     savings
    -0.06
    ç¾
    -0.06
    ç±į
    -0.06
    birthdate
    -0.06
    ported
    -0.06
    POSITIVE LOGITS
    SSERT
    0.07
    direct
    0.07
     Bid
    0.06
     Banner
    0.06
    _fmt
    0.06
    acket
    0.06
     Keyword
    0.06
    hti
    0.06
    izza
    0.06
    SES
    0.06
    Activations Density 0.003%

    No Known Activations