© 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. 127449
    Prev
    Next
    INDEX
    Explanations

    references to free or no-cost offers and promotions

    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
     dese
    -0.06
    AIL
    -0.06
    spath
    -0.06
    agina
    -0.06
    .Cryptography
    -0.06
    æķ
    -0.06
    سد
    -0.06
     unborn
    -0.06
     sooner
    -0.06
    _OPENGL
    -0.06
    POSITIVE LOGITS
     free
    0.08
    Gratis
    0.07
    free
    0.07
     gratis
    0.07
    uper
    0.07
    assin
    0.07
    rico
    0.07
    nge
    0.07
     Minds
    0.06
     Free
    0.06
    Activations Density 0.003%

    No Known Activations