© 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. 17-LLAMASCOPE-RES-131K
    11. 56495
    Prev
    Next
    INDEX
    Explanations

    multiple mentions of the word "Rights" and related phrases

    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
     Dam
    -0.07
    eness
    -0.07
    ampton
    -0.07
    ugs
    -0.07
     Hilton
    -0.06
    eil
    -0.06
     Saud
    -0.06
    ku
    -0.06
    Ŀ
    -0.06
    Ãłm
    -0.06
    POSITIVE LOGITS
     abs
    0.07
    apos
    0.07
    rong
    0.07
    LR
    0.06
    iano
    0.06
    arks
    0.06
    unas
    0.06
    copyright
    0.06
     ©
    0.06
    edes
    0.06
    Activations Density 0.003%

    No Known Activations