© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 77822
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    enheim
    -0.07
     Ashe
    -0.07
    ierz
    -0.06
    omez
    -0.06
     Tradable
    -0.06
    etty
    -0.06
    LIKELY
    -0.06
    Ñıж
    -0.06
    lide
    -0.06
    lut
    -0.06
    POSITIVE LOGITS
    uito
    0.06
    loy
    0.06
    ocard
    0.06
    KE
    0.06
    ukan
    0.06
    olut
    0.06
    _cv
    0.06
    надлеж
    0.06
    orem
    0.06
    ÙĨج
    0.06
    Activations Density 0.000%

    No Known Activations