© 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. 15-LLAMASCOPE-RES-131K
    11. 88487
    Prev
    Next
    INDEX
    Explanations

    HTML or code-related formatting tags

    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
    y
    -0.06
    iving
    -0.06
     Vic
    -0.06
    ib
    -0.06
    iga
    -0.06
    iver
    -0.06
    ERM
    -0.06
    atar
    -0.05
    an
    -0.05
     dap
    -0.05
    POSITIVE LOGITS
    課
    0.07
     تÙĪس
    0.07
    ERRU
    0.07
     trÆ°á»Łng
    0.07
    adamente
    0.07
    GGLE
    0.07
    odox
    0.07
    ikler
    0.07
    ginas
    0.07
    ãĤŃãĥ¥
    0.07
    Activations Density 0.000%

    No Known Activations