© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 83140
    Prev
    Next
    INDEX
    Explanations

    identifiers and codes associated with specific items or concepts

    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
    UNUSED
    -0.07
    enge
    -0.07
    ilst
    -0.07
     WithEvents
    -0.07
    ereotype
    -0.07
    kiem
    -0.06
    OMPI
    -0.06
    rana
    -0.06
    kil
    -0.06
    icity
    -0.06
    POSITIVE LOGITS
    ustr
    0.06
    olt
    0.06
     Voor
    0.06
    razier
    0.06
    .biz
    0.06
    _GP
    0.06
    akter
    0.05
    ÄĻd
    0.05
     Operand
    0.05
     nackte
    0.05
    Activations Density 0.031%

    No Known Activations