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

    Neuronpedia

    Jacobian LensNEW
    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. 87479
    Prev
    Next
    INDEX
    Explanations

    terms related to data formats and arithmetic operations

    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
    ogan
    -0.06
    wins
    -0.06
    asar
    -0.06
    ÙĪگر
    -0.06
     ig
    -0.06
     Gron
    -0.06
    igi
    -0.06
    urret
    -0.06
    ogle
    -0.06
    ëĵ¯
    -0.06
    POSITIVE LOGITS
    sthrough
    0.06
    ("(%
    0.06
     Overse
    0.06
    abus
    0.06
    irim
    0.06
    ÐIJÑĢÑħÑĸв
    0.06
    ertime
    0.06
     Tues
    0.06
    inati
    0.06
    cntl
    0.06
    Activations Density 0.000%

    No Known Activations