© 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. 105871
    Prev
    Next
    INDEX
    Explanations

    issues related to mechanical malfunctions or repairs

    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
    igators
    -0.07
     IRequest
    -0.07
    ache
    -0.07
     OnTriggerEnter
    -0.07
    ãĥ³ãĥij
    -0.06
    quete
    -0.06
    ForResult
    -0.06
    __;↵
    -0.06
     Launcher
    -0.06
    optera
    -0.06
    POSITIVE LOGITS
    PN
    0.07
     fou
    0.06
    ï¼
    0.06
    è¯Ĭ
    0.06
     sto
    0.06
     millennium
    0.06
     Millennium
    0.06
     elim
    0.06
    鼨
    0.06
    itemap
    0.06
    Activations Density 0.009%

    No Known Activations