© 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. 126534
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emotions and commitments related to artistic or personal endeavors

    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
    baugh
    -0.06
    .setColumn
    -0.06
    laus
    -0.06
     StringBuffer
    -0.06
    arcy
    -0.06
    alte
    -0.06
    etti
    -0.06
     danmark
    -0.06
    /mac
    -0.06
    rieving
    -0.06
    POSITIVE LOGITS
     drive
    0.08
     drives
    0.07
    -drive
    0.07
     clashes
    0.07
     doÄŁrult
    0.07
     growing
    0.06
     Drive
    0.06
    ALS
    0.06
    pq
    0.06
     deep
    0.06
    Activations Density 0.044%

    No Known Activations