© 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. 54391
    Prev
    Next
    INDEX
    Explanations

    HTML table elements and their attributes in a document

    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
    aley
    -0.06
     Bugs
    -0.06
    çŃij
    -0.06
    handleRequest
    -0.06
    lider
    -0.06
    дÑĥ
    -0.06
    IRMWARE
    -0.06
     Lowell
    -0.06
    ">//
    -0.05
     NSK
    -0.05
    POSITIVE LOGITS
    KIT
    0.07
    нез
    0.07
    å°¾
    0.07
    psilon
    0.07
    /stdc
    0.07
    nable
    0.07
    tvrt
    0.06
    edList
    0.06
    оÑĢони
    0.06
    sym
    0.06
    Activations Density 0.001%

    No Known Activations