© 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. 9-LLAMASCOPE-RES-131K
    11. 95578
    Prev
    Next
    INDEX
    Explanations

    references to military-related terms and 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
    stvo
    -0.07
    istrovstvÃŃ
    -0.07
    laus
    -0.07
    ÙĨ
    -0.07
    heim
    -0.07
     moot
    -0.07
    idas
    -0.07
    sto
    -0.06
    stå
    -0.06
    piry
    -0.06
    POSITIVE LOGITS
    çĦ¶
    0.07
    ÚĨÙĩ
    0.07
    .sourceforge
    0.06
    tainment
    0.06
    oise
    0.06
    /nav
    0.06
    ompiler
    0.06
    IAL
    0.06
    ì²ł
    0.06
    YPE
    0.06
    Activations Density 0.017%

    No Known Activations