© 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. 123809
    Prev
    Next
    INDEX
    Explanations

    key performance metrics and definitions relating to accuracy and evaluation in various contexts

    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
    outil
    -0.08
    alta
    -0.08
    oreach
    -0.07
    ืà¸Ńà¸Ĥ
    -0.07
    anz
    -0.07
     Äijây
    -0.07
     ÄĮer
    -0.07
    opsy
    -0.07
    ilo
    -0.07
    amoto
    -0.06
    POSITIVE LOGITS
     elsewhere
    0.10
     used
    0.07
     seen
    0.07
     previous
    0.07
     other
    0.06
     previously
    0.06
     earlier
    0.06
     similarly
    0.06
    fare
    0.06
    fa
    0.06
    Activations Density 0.054%

    No Known Activations