© 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. 75503
    Prev
    Next
    INDEX
    Explanations

    references to scientific papers or articles

    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
     miscellaneous
    -0.07
    Disposed
    -0.07
    thing
    -0.07
    loff
    -0.07
    lix
    -0.06
    ownik
    -0.06
    ala
    -0.06
    hap
    -0.06
    olg
    -0.06
    azen
    -0.06
    POSITIVE LOGITS
    ãĥ§
    0.06
    ä¸ĸç´Ģ
    0.06
    ãĢij,
    0.06
    aina
    0.06
    κι
    0.06
     ÙĥÙĬÙĦ
    0.06
    оки
    0.06
    ummer
    0.06
     Laden
    0.06
     Decompiled
    0.06
    Activations Density 0.002%

    No Known Activations