© 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. 17-LLAMASCOPE-RES-131K
    11. 94963
    Prev
    Next
    INDEX
    Explanations

    monetary values and pricing information

    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
    énom
    -0.07
    709
    -0.06
    opot
    -0.06
     عÙĤد
    -0.06
    ниÑĨÑı
    -0.06
    duct
    -0.06
    hiba
    -0.06
    809
    -0.06
    ŀ
    -0.06
    etter
    -0.06
    POSITIVE LOGITS
    ä¸Ī
    0.08
    abor
    0.07
    oday
    0.07
    openhagen
    0.07
    eba
    0.06
    CLUDING
    0.06
     Bailey
    0.06
    inos
    0.06
    HC
    0.06
    technical
    0.06
    Activations Density 0.002%

    No Known Activations