© 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. 29360
    Prev
    Next
    INDEX
    Explanations

    terms related to waveguides and their properties

    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
    aben
    -0.07
    aster
    -0.07
     вдÑĢÑĥг
    -0.07
    axed
    -0.07
     Fior
    -0.07
    irsch
    -0.07
    esty
    -0.07
    олж
    -0.06
    idot
    -0.06
    Ñĸж
    -0.06
    POSITIVE LOGITS
     tys
    0.06
    éĿ©
    0.06
     commonly
    0.06
    mn
    0.06
    _common
    0.06
    Manchester
    0.06
     designs
    0.06
    ħn
    0.06
     Designs
    0.06
    chemes
    0.06
    Activations Density 0.028%

    No Known Activations