© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 41212
    Prev
    Next
    INDEX
    Explanations

    information related to scientific research and data analysis

    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
    folio
    -0.07
    ittel
    -0.06
    zt
    -0.06
    OTP
    -0.06
    claim
    -0.06
    bee
    -0.06
     Hlav
    -0.06
    оÑĢи
    -0.06
    byn
    -0.06
    categorie
    -0.06
    POSITIVE LOGITS
     Dx
    0.07
     large
    0.06
     dataSize
    0.06
    STYPE
    0.06
    ìn
    0.06
     distant
    0.06
    actic
    0.06
     editorial
    0.06
    ILog
    0.06
    поÑĢ
    0.06
    Activations Density 0.003%

    No Known Activations