© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103875
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and file extensions

    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
    alen
    -0.06
    ÙĪÙĦØ©
    -0.06
    ANGED
    -0.06
    CppType
    -0.06
    562
    -0.06
    evin
    -0.06
    sip
    -0.06
    elman
    -0.06
     wen
    -0.06
    .SizeType
    -0.06
    POSITIVE LOGITS
    REC
    0.06
     hei
    0.06
     apart
    0.06
    ums
    0.06
    udies
    0.06
    igroup
    0.06
    modo
    0.06
    ellas
    0.06
    Та
    0.06
     allot
    0.06
    Activations Density 0.003%

    No Known Activations