© 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. 15-LLAMASCOPE-RES-131K
    11. 90538
    Prev
    Next
    INDEX
    Explanations

    numerical data and percentages related to production statistics

    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
     rarity
    -0.06
    asil
    -0.06
    ICLE
    -0.06
    eca
    -0.06
    $MESS
    -0.06
    ATA
    -0.06
    haled
    -0.06
    ɵ
    -0.06
     Mill
    -0.06
    aca
    -0.06
    POSITIVE LOGITS
    lü
    0.07
     last
    0.07
    мени
    0.07
    uchs
    0.07
     tÄĥng
    0.07
    icolor
    0.07
    課
    0.06
    มà¸Ĥ
    0.06
    ục
    0.06
    ifar
    0.06
    Activations Density 0.010%

    No Known Activations