© 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. 77112
    Prev
    Next
    INDEX
    Explanations

    numerical patterns or statistics

    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
     Blocked
    -0.06
    ĮĴ
    -0.06
    ESIS
    -0.06
    اخت
    -0.06
     anzeigen
    -0.06
     Fountain
    -0.06
    esis
    -0.06
     totiž
    -0.06
    ÑĢоÑģÑĤ
    -0.06
     niche
    -0.06
    POSITIVE LOGITS
    otec
    0.08
    оÑİ
    0.07
    ignKey
    0.07
    icode
    0.07
    poons
    0.07
    Bru
    0.06
    ANJI
    0.06
    Corner
    0.06
    tingham
    0.06
    .raises
    0.06
    Activations Density 0.010%

    No Known Activations