© 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 EvalsExportsAPI 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. 61071
    Prev
    Next
    INDEX
    Explanations

    phrases related to dental procedures and implants

    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
    ipar
    -0.07
    รà¸ĵ
    -0.07
    gua
    -0.07
    γο
    -0.07
    ä¸įå¾Ĺ
    -0.07
    æĬij
    -0.07
    -js
    -0.07
    iso
    -0.06
    lyph
    -0.06
    (Paint
    -0.06
    POSITIVE LOGITS
    -anchor
    0.09
     anchor
    0.09
     anch
    0.08
     anchors
    0.08
    anchors
    0.08
     Anchor
    0.07
    ecure
    0.07
     titanium
    0.07
    anchor
    0.06
    _anchor
    0.06
    Activations Density 0.002%

    No Known Activations