© 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. 130392
    Prev
    Next
    INDEX
    Explanations

    numbers and identifiers related to technical specifications or programming contexts

    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
    achs
    -0.08
    olla
    -0.08
    ventus
    -0.07
    rios
    -0.07
    irl
    -0.07
    ECTOR
    -0.07
    ureau
    -0.07
    ovi
    -0.07
    krit
    -0.06
    raž
    -0.06
    POSITIVE LOGITS
     Symbols
    0.07
     âĢIJ
    0.07
     âĢª
    0.06
    0.06
    atatype
    0.06
     consolidate
    0.06
    δÏĮ
    0.06
     Trident
    0.06
    _commit
    0.06
    åģ
    0.06
    Activations Density 0.011%

    No Known Activations