© 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. 2189
    Prev
    Next
    INDEX
    Explanations

    terms related to business achievements and customer solutions

    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
    rists
    -0.07
    isons
    -0.07
    ocard
    -0.07
    cimal
    -0.07
    gles
    -0.06
     slu
    -0.06
    antaged
    -0.06
    ocre
    -0.06
    åij
    -0.06
    oscope
    -0.06
    POSITIVE LOGITS
    amarin
    0.06
    .rad
    0.06
     innovation
    0.06
    PÅĻÃŃ
    0.06
    abr
    0.06
    à¸IJ
    0.06
    inn
    0.06
    -java
    0.05
     tang
    0.05
    anne
    0.05
    Activations Density 0.004%

    No Known Activations