© 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. 57566
    Prev
    Next
    INDEX
    Explanations

    numerical scores and outcomes in competitive scenarios

    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
    gom
    -0.08
    aran
    -0.08
    odox
    -0.07
    osy
    -0.07
    forge
    -0.07
    odos
    -0.07
     Watts
    -0.07
    oÄŁ
    -0.07
    hud
    -0.07
    dic
    -0.07
    POSITIVE LOGITS
    /-
    0.08
    âĢ³
    0.07
    iyon
    0.06
    ugen
    0.06
    ideos
    0.06
    issa
    0.06
    iken
    0.05
     prev
    0.05
     final
    0.05
    .ua
    0.05
    Activations Density 0.014%

    No Known Activations