© 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. 106723
    Prev
    Next
    INDEX
    Explanations

    numerical or statistical data

    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
    esan
    -0.07
    edy
    -0.07
    \uc
    -0.06
    essian
    -0.06
    दर
    -0.06
    Äįen
    -0.06
    LK
    -0.06
     Th
    -0.06
    entin
    -0.06
    uze
    -0.06
    POSITIVE LOGITS
    VERR
    0.07
    _amp
    0.06
    asha
    0.06
    à¥įतà¤ķ
    0.06
    ymb
    0.06
    æĪı
    0.06
    verte
    0.06
    udd
    0.06
     Dew
    0.06
    327
    0.06
    Activations Density 0.001%

    No Known Activations