© 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. 60844
    Prev
    Next
    INDEX
    Explanations

    terms related to construction and maintenance processes

    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
    ieren
    -0.07
    istrovstvÃŃ
    -0.07
    .cum
    -0.07
    utorials
    -0.07
    quila
    -0.07
     grou
    -0.06
     upkeep
    -0.06
    ScreenWidth
    -0.06
    /csv
    -0.06
    STRUCTOR
    -0.06
    POSITIVE LOGITS
     IIC
    0.08
     drying
    0.07
     Hod
    0.06
    ITU
    0.06
    orris
    0.06
    ovÄĽ
    0.06
    zilla
    0.06
     flooding
    0.06
     flood
    0.06
     mop
    0.06
    Activations Density 0.001%

    No Known Activations