© 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. 86233
    Prev
    Next
    INDEX
    Explanations

    capital letters or specific sense of naming conventions

    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
    TOTYPE
    -0.07
    OLEAN
    -0.07
    ypi
    -0.07
    лÑıд
    -0.07
    929
    -0.07
    ivant
    -0.07
    mour
    -0.06
     recomm
    -0.06
    IMITER
    -0.06
    iface
    -0.06
    POSITIVE LOGITS
    ebin
    0.06
    ·
    0.06
    lington
    0.06
     Neal
    0.06
    olars
    0.06
     ----------------------------------------------------------------------↵
    0.06
    orate
    0.06
    atre
    0.06
     tslint
    0.06
    openhagen
    0.06
    Activations Density 0.005%

    No Known Activations