© 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. 98325
    Prev
    Next
    INDEX
    Explanations

    relationships and structures within complex systems

    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
    ylon
    -0.08
    blr
    -0.07
    vrd
    -0.07
    Latch
    -0.07
    emd
    -0.07
    anter
    -0.07
    ITES
    -0.06
    à¹Ģà¸Ńà¸ĩ
    -0.06
    svm
    -0.06
    jec
    -0.06
    POSITIVE LOGITS
    arris
    0.06
    combe
    0.06
     Harris
    0.06
    _uc
    0.06
    æ´Ľ
    0.06
     Lind
    0.06
     suppression
    0.05
    ombo
    0.05
    bits
    0.05
    äge
    0.05
    Activations Density 0.190%

    No Known Activations