© 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. 62473
    Prev
    Next
    INDEX
    Explanations

    colons and words related to vibrant attributes or descriptions

    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
    ourg
    -0.07
    itou
    -0.06
    elen
    -0.06
    عدد
    -0.06
    iam
    -0.06
    iac
    -0.06
    =default
    -0.06
    ITU
    -0.06
    225
    -0.06
    اخ
    -0.06
    POSITIVE LOGITS
    inalg
    0.07
    edBy
    0.06
    ofire
    0.06
    zon
    0.06
    rier
    0.06
    edis
    0.06
    Tw
    0.06
    antages
    0.06
    ORED
    0.06
    _callbacks
    0.06
    Activations Density 0.000%

    No Known Activations