© 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. 15-LLAMASCOPE-RES-131K
    11. 87710
    Prev
    Next
    INDEX
    Explanations

    concepts related to spacing and arrangement

    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
     scissors
    -0.07
    ÄĽÅ¾
    -0.06
    kovi
    -0.06
    undles
    -0.06
    rame
    -0.06
    isty
    -0.06
    xaa
    -0.06
    enz
    -0.06
    alice
    -0.06
    @show
    -0.06
    POSITIVE LOGITS
     between
    0.08
     spacing
    0.07
     intervals
    0.07
    ระหว
    0.07
    _between
    0.07
     interval
    0.07
     междÑĥ
    0.07
    acing
    0.07
    (interval
    0.07
     мÑĸж
    0.07
    Activations Density 0.020%

    No Known Activations