© 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. 56928
    Prev
    Next
    INDEX
    Explanations

    blocks of code or structural elements in programming languages

    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
    ards
    -0.07
    shift
    -0.07
     обоÑĢ
    -0.07
    abis
    -0.06
    asty
    -0.06
    elm
    -0.06
    ãĥ¥ãĥ¼
    -0.06
    ownt
    -0.06
    uide
    -0.06
    etim
    -0.06
    POSITIVE LOGITS
     trump
    0.07
    raj
    0.07
    год
    0.06
    reopen
    0.06
    _UNS
    0.06
    аÑĢан
    0.06
     Shay
    0.06
    ì°©
    0.06
    XL
    0.06
    ÛĮÙĩ
    0.06
    Activations Density 0.003%

    No Known Activations