© 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. 89013
    Prev
    Next
    INDEX
    Explanations

    references to accounts or enrollment processes related to applications

    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
     _
    -0.07
    ↵
    -0.06
    odos
    -0.06
    arend
    -0.06
     even
    -0.06
    але
    -0.06
    iy
    -0.06
    [
    -0.06
    ington
    -0.06
    jie
    -0.06
    POSITIVE LOGITS
    ä½łçļĦ
    0.09
     your
    0.09
    roti
    0.09
    your
    0.08
     sẽ
    0.08
     bÄĻd
    0.08
    will
    0.08
    zdy
    0.08
     budete
    0.08
     will
    0.08
    Activations Density 0.019%

    No Known Activations