© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 40370
    Prev
    Next
    INDEX
    Explanations

    financial metrics and business performance indicators

    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
    orde
    -0.06
    osit
    -0.06
     gezocht
    -0.06
    _totals
    -0.06
    UX
    -0.06
    è¸ı
    -0.06
     subsequ
    -0.06
    olo
    -0.06
     cigars
    -0.06
    anzeigen
    -0.06
    POSITIVE LOGITS
    rank
    0.07
    lan
    0.07
     rival
    0.07
     rank
    0.06
    zych
    0.06
    Aceptar
    0.06
    annes
    0.06
    öm
    0.06
     Abilities
    0.06
    Impl
    0.06
    Activations Density 0.023%

    No Known Activations