Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 106674
    Prev
    Next
    INDEX
    Explanations

    references to corresponding elements or relationships in data and equations

    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
    γοÏħ
    -0.07
     Luc
    -0.06
    anka
    -0.06
    pac
    -0.06
    оÑĢÑĭ
    -0.06
    олÑĸ
    -0.06
    ensing
    -0.06
    ime
    -0.06
    assen
    -0.06
    isel
    -0.06
    POSITIVE LOGITS
    ingly
    0.09
    ToSelector
    0.08
    avl
    0.08
    vais
    0.08
    //{{
    0.08
    OffsetTable
    0.07
    ÙĦع
    0.07
     Gallup
    0.07
    CppClass
    0.07
    'gc
    0.07
    Activations Density 0.010%

    No Known Activations