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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 57866
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to governance and organizational structure

    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
    ạp
    -0.08
    isos
    -0.07
    iej
    -0.07
    BuilderInterface
    -0.07
    леж
    -0.07
    aniem
    -0.07
    otts
    -0.07
    /lic
    -0.07
    lore
    -0.06
    ůj
    -0.06
    POSITIVE LOGITS
     salary
    0.07
     resign
    0.07
     rem
    0.07
     travel
    0.06
     term
    0.06
     salaries
    0.06
     pec
    0.06
     compensation
    0.06
     tem
    0.06
     tet
    0.06
    Activations Density 0.003%

    No Known Activations