© 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. 91903
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations

    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
     Nelson
    -0.06
    INSTANCE
    -0.06
    yor
    -0.06
     Globals
    -0.06
    ifie
    -0.06
     Leaf
    -0.06
    fried
    -0.06
     INSTANCE
    -0.06
     Introduced
    -0.06
     Charl
    -0.06
    POSITIVE LOGITS
    olini
    0.07
    achen
    0.07
    .range
    0.07
    .Range
    0.07
     range
    0.07
    (range
    0.07
    .arange
    0.07
    ÑĢаÑģÑĤа
    0.07
    gamber
    0.06
    ием
    0.06
    Activations Density 0.014%

    No Known Activations