© 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. 76419
    Prev
    Next
    INDEX
    Explanations

    instructions related to proper maintenance and installation techniques

    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
     actionTypes
    -0.08
    ãĥ¼ãĥĢ
    -0.08
    ewe
    -0.07
    ystack
    -0.07
    uada
    -0.07
    agate
    -0.07
    redo
    -0.07
    è¿IJåĬ¨
    -0.07
    stva
    -0.06
     pás
    -0.06
    POSITIVE LOGITS
     start
    0.07
    start
    0.07
    -start
    0.06
     START
    0.06
     begin
    0.06
     Start
    0.06
     Kre
    0.06
    _Start
    0.06
     starts
    0.06
     first
    0.06
    Activations Density 0.020%

    No Known Activations