© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118939
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating a relationship or connection

    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
    OrElse
    -0.07
    çĤ
    -0.07
     пÑĢид
    -0.07
    cxx
    -0.07
    inspection
    -0.06
    _defaults
    -0.06
    Ñĸб
    -0.06
    ãĥ¼ãĥ©
    -0.06
    hawk
    -0.06
    spath
    -0.06
    POSITIVE LOGITS
     twin
    0.07
    LEGRO
    0.07
    isa
    0.07
     crossorigin
    0.07
    uty
    0.06
    ambi
    0.06
    uras
    0.06
    unate
    0.06
    StorageSync
    0.06
    /or
    0.06
    Activations Density 0.019%

    No Known Activations