© 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. 54833
    Prev
    Next
    INDEX
    Explanations

    constructions referring to various technical embodiments or configurations

    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
    aval
    -0.07
    ÙĪÙħ
    -0.06
    itemap
    -0.06
    enco
    -0.06
    adies
    -0.06
    kening
    -0.06
    tul
    -0.06
    amac
    -0.06
    lander
    -0.06
     Helm
    -0.06
    POSITIVE LOGITS
     développ
    0.07
     thang
    0.06
    utin
    0.06
     calend
    0.06
    اÙĪÙĩ
    0.06
     commercially
    0.06
     comercial
    0.05
    ITT
    0.05
     âĹĦ
    0.05
    thood
    0.05
    Activations Density 0.067%

    No Known Activations