© 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. 17-LLAMASCOPE-RES-131K
    11. 128970
    Prev
    Next
    INDEX
    Explanations

    specific phrases indicating functionality and performance benefits

    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
    ạnh
    -0.07
    аÑĢи
    -0.07
     Rath
    -0.07
    ombat
    -0.06
    AMI
    -0.06
     Joyce
    -0.06
    PRS
    -0.06
     Py
    -0.06
    umer
    -0.06
    pei
    -0.06
    POSITIVE LOGITS
     можно
    0.07
    rint
    0.06
    ipo
    0.06
    ÃĹ↵↵
    0.06
    gi
    0.06
    sten
    0.06
    cken
    0.06
     можна
    0.06
    rek
    0.06
    _subtitle
    0.06
    Activations Density 0.025%

    No Known Activations