© 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. 15-LLAMASCOPE-RES-131K
    6. 26434
    Prev
    Next
    INDEX
    Explanations

    references to structural components and their arrangements in systems or mechanisms

    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
    933
    -0.06
    zin
    -0.06
    /Branch
    -0.06
     omas
    -0.06
     ur
    -0.06
    idir
    -0.06
     Tang
    -0.05
    urve
    -0.05
    IA
    -0.05
    ä¹Ī
    -0.05
    POSITIVE LOGITS
    ikal
    0.09
    íĴĪ
    0.08
     Shapiro
    0.07
    fuscated
    0.07
    ensemble
    0.06
    aghan
    0.06
    addin
    0.06
    prise
    0.06
     ensemble
    0.06
    .Transactional
    0.06
    Activations Density 0.035%

    No Known Activations