© 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. 9-LLAMASCOPE-RES-131K
    11. 94560
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and specific formatting features in written 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
    avage
    -0.06
    çĽijåIJ¬é¡µéĿ¢
    -0.06
    ington
    -0.06
    ghi
    -0.06
    .increment
    -0.06
    axe
    -0.06
    isu
    -0.06
     Slater
    -0.06
    IBUTE
    -0.06
    ään
    -0.06
    POSITIVE LOGITS
    uro
    0.06
    AMI
    0.06
    뢰
    0.06
    issing
    0.06
    ingo
    0.06
     çĬ
    0.06
    ancies
    0.06
    ncy
    0.06
    sez
    0.06
     ç¾
    0.06
    Activations Density 0.013%

    No Known Activations