© 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. 128858
    Prev
    Next
    INDEX
    Explanations

    historical references and dates

    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
    ocks
    -0.07
    ingo
    -0.07
     job
    -0.06
    ãĥĩãĤ£ãĤ¢
    -0.06
    unge
    -0.06
    ajas
    -0.06
    uste
    -0.06
     sep
    -0.06
    PAD
    -0.06
     Charging
    -0.06
    POSITIVE LOGITS
     podrob
    0.07
    orda
    0.07
     ulus
    0.06
    ávka
    0.06
    _checkpoint
    0.06
    axis
    0.06
     згÑĸдно
    0.06
    ModelProperty
    0.06
    alytics
    0.06
    checkpoint
    0.06
    Activations Density 0.009%

    No Known Activations