© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97491
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" indicating existence or state

    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
     ç·
    -0.07
    eb
    -0.07
    mmas
    -0.07
    ounge
    -0.06
    æľīçļĦ
    -0.06
     ëĦ¤ìĿ´íĬ¸
    -0.06
    KA
    -0.06
    empo
    -0.06
    /XML
    -0.06
    skyt
    -0.06
    POSITIVE LOGITS
    γει
    0.08
    rale
    0.07
    elage
    0.07
    éĩı
    0.06
     relief
    0.06
    /is
    0.06
    _ble
    0.06
     Relief
    0.06
    uria
    0.06
     SetLastError
    0.06
    Activations Density 0.075%

    No Known Activations