© 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. 95692
    Prev
    Next
    INDEX
    Explanations

    references to legal or constitutional documents

    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
    aping
    -0.07
     activeClassName
    -0.06
    ynet
    -0.06
     Mang
    -0.06
    d
    -0.06
    ija
    -0.06
    925
    -0.06
     we
    -0.06
     mang
    -0.05
     bus
    -0.05
    POSITIVE LOGITS
    _handlers
    0.07
    адж
    0.07
     Hung
    0.07
    Å©i
    0.07
    idy
    0.07
    ennes
    0.07
    ãģ¨ãģĨ
    0.07
    ÑĪкÑĥ
    0.07
    ÑĢеÑĪ
    0.07
    ÑĢазд
    0.07
    Activations Density 0.001%

    No Known Activations