© 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. 86861
    Prev
    Next
    INDEX
    Explanations

    issues related to coding errors and problems in parameters or data assignments

    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
    ashi
    -0.07
    lds
    -0.07
    iale
    -0.07
    holder
    -0.07
    hud
    -0.06
    xDB
    -0.06
    quier
    -0.06
    ãģĵãĤĵãģ«
    -0.06
     IG
    -0.06
    lice
    -0.06
    POSITIVE LOGITS
     fault
    0.06
     correctly
    0.06
     correct
    0.06
     oder
    0.06
     либо
    0.06
    pedo
    0.06
    correct
    0.06
    .Cancel
    0.06
     fundamentals
    0.06
    roscope
    0.05
    Activations Density 0.008%

    No Known Activations