© 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. 3257
    Prev
    Next
    INDEX
    Explanations

    references to naval warfare and submarine activities

    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
    éĢīæĭ
    -0.07
    ihan
    -0.07
     MANUAL
    -0.06
    Streams
    -0.06
    _streams
    -0.06
    owell
    -0.06
    ertiary
    -0.06
    è¡Ľ
    -0.06
     manual
    -0.06
     Mong
    -0.06
    POSITIVE LOGITS
    neau
    0.07
     escort
    0.07
    vore
    0.07
     escorted
    0.06
     CVE
    0.06
     radio
    0.06
    õi
    0.06
     Escort
    0.06
     escorts
    0.06
     radar
    0.06
    Activations Density 0.017%

    No Known Activations