© 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. 15-LLAMASCOPE-RES-131K
    11. 87773
    Prev
    Next
    INDEX
    Explanations

    references to mining and environmental assessments

    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
    TRACE
    -0.07
    /rfc
    -0.07
    æĻ¯
    -0.07
    CCI
    -0.07
    boa
    -0.07
    éĽij
    -0.06
    ÅĽci
    -0.06
    iterals
    -0.06
     Bout
    -0.06
     æĻ´
    -0.06
    POSITIVE LOGITS
     inherited
    0.06
     underlying
    0.06
     potential
    0.06
     veins
    0.06
     vein
    0.06
     Targets
    0.06
    _dispatch
    0.06
    inka
    0.06
     target
    0.06
     kim
    0.06
    Activations Density 0.005%

    No Known Activations