© 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. 74880
    Prev
    Next
    INDEX
    Explanations

    terms related to product safety and regulatory compliance

    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
    762
    -0.07
    tour
    -0.07
    dj
    -0.06
    gas
    -0.06
    ulla
    -0.06
    ìłĪ
    -0.06
     pne
    -0.06
    atti
    -0.06
     cryptoc
    -0.06
    leaf
    -0.06
    POSITIVE LOGITS
     bis
    0.08
     plastic
    0.07
     estrogen
    0.07
     Ches
    0.07
     Cypress
    0.06
     horm
    0.06
    ecycle
    0.06
     Nile
    0.06
    ÑĪки
    0.06
     hormone
    0.06
    Activations Density 0.003%

    No Known Activations