© 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. 73098
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mendel" and its variations

    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
    ëį°ìĿ´íĬ¸
    -0.10
    .Automation
    -0.08
    onis
    -0.08
    akter
    -0.07
    ì¸ł
    -0.07
    ieri
    -0.07
    erals
    -0.07
    MMM
    -0.07
    کت
    -0.07
     вк
    -0.07
    POSITIVE LOGITS
     Madness
    0.08
    el
    0.08
    rick
    0.06
     mini
    0.06
    oc
    0.06
    ew
    0.06
    rix
    0.06
    agram
    0.06
    apatkan
    0.06
     furn
    0.06
    Activations Density 0.004%

    No Known Activations