© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129735
    Prev
    Next
    INDEX
    Explanations

    references to reporting mechanisms and standards of conduct

    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
    æŃ¡
    -0.06
    ĥ½
    -0.06
     massaggi
    -0.06
     kop
    -0.06
    avl
    -0.06
    ÙħÙĩ
    -0.06
    енд
    -0.06
    रण
    -0.06
     interrog
    -0.06
    ableViewController
    -0.06
    POSITIVE LOGITS
    WT
    0.07
     Moder
    0.07
    oref
    0.06
    XT
    0.06
     flag
    0.06
     Lucia
    0.06
     Giul
    0.06
     bad
    0.06
    ab
    0.06
    PCI
    0.06
    Activations Density 0.009%

    No Known Activations