© 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. 72144
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their context in the text

    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
    ataka
    -0.07
    »¿
    -0.07
    alars
    -0.07
    åİŁæĿ¥
    -0.07
    ENTE
    -0.07
    usercontent
    -0.07
    lify
    -0.06
    lü
    -0.06
    tem
    -0.06
    ificador
    -0.06
    POSITIVE LOGITS
     recently
    0.08
     recent
    0.08
     witness
    0.07
     consider
    0.07
    recent
    0.07
    Recently
    0.07
     Recently
    0.06
     Witness
    0.06
     examples
    0.06
    attles
    0.06
    Activations Density 0.033%

    No Known Activations