© 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. 107084
    Prev
    Next
    INDEX
    Explanations

    references to programming languages, libraries, or frameworks

    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
    ñana
    -0.07
    Ì
    -0.07
    rez
    -0.06
    &_
    -0.06
    illon
    -0.06
    inf
    -0.06
     Vij
    -0.06
    ̣
    -0.06
    pell
    -0.06
    peak
    -0.06
    POSITIVE LOGITS
    adesh
    0.07
    hiba
    0.07
    лÑİд
    0.06
     Bounty
    0.06
    ERO
    0.06
    tuk
    0.06
     IMPLIED
    0.06
    ohl
    0.06
    stu
    0.06
    astos
    0.06
    Activations Density 0.003%

    No Known Activations