© 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. 9-LLAMASCOPE-RES-131K
    11. 97629
    Prev
    Next
    INDEX
    Explanations

    elements related to formal roles or functions within organizations

    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
     ç©
    -0.07
    probe
    -0.07
    FRING
    -0.07
    esco
    -0.06
    _probe
    -0.06
    ddit
    -0.06
    ETHER
    -0.06
     Probe
    -0.06
    Probe
    -0.06
    à¤¿à¤ľ
    -0.06
    POSITIVE LOGITS
    inde
    0.07
    322
    0.07
     Clarkson
    0.07
     Klo
    0.07
    ins
    0.06
    UNUSED
    0.06
    ipt
    0.06
    ree
    0.06
     Hunt
    0.06
    ain
    0.06
    Activations Density 0.223%

    No Known Activations