© 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. 86791
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and sentence ends

    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
     ÐļÑĢÑĸм
    -0.08
    غة
    -0.07
    ERP
    -0.07
    oyer
    -0.07
    eda
    -0.07
    еком
    -0.07
    erah
    -0.07
    $__
    -0.07
    anela
    -0.07
    illet
    -0.07
    POSITIVE LOGITS
    ugo
    0.06
     mar
    0.06
    ammer
    0.06
    Âł
    0.06
    0.06
     “
    0.06
     resistance
    0.06
    ovol
    0.06
    annon
    0.05
    AAD
    0.05
    Activations Density 0.001%

    No Known Activations