© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57473
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those associated with counts or measurements

    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
    üb
    -0.07
     furniture
    -0.07
    622
    -0.06
    .dot
    -0.06
    822
    -0.06
    .openConnection
    -0.06
    #w
    -0.06
     Furniture
    -0.06
    æŁ´
    -0.06
    ÑĢаÑģÑĤ
    -0.06
    POSITIVE LOGITS
    pace
    0.07
    รà¸ĵ
    0.07
    missions
    0.07
     Ros
    0.06
     Laure
    0.06
    Ros
    0.06
    /Grid
    0.06
     Tub
    0.06
    tasks
    0.06
    dlg
    0.06
    Activations Density 0.003%

    No Known Activations