© 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. 126012
    Prev
    Next
    INDEX
    Explanations

    terms related to software add-ons and modifications

    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
    lernen
    -0.07
    erken
    -0.07
    meric
    -0.07
     Cant
    -0.06
     mj
    -0.06
    jr
    -0.06
    fon
    -0.06
    /people
    -0.06
     trh
    -0.06
    lig
    -0.06
    POSITIVE LOGITS
    .createFrom
    0.07
    turnstile
    0.06
    -enabled
    0.06
     Premi
    0.06
    âĢĮâĢĮ
    0.06
     Barrel
    0.06
    ForObject
    0.06
    aim
    0.06
     èĢ
    0.06
    .Debugger
    0.06
    Activations Density 0.025%

    No Known Activations