© 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. 128517
    Prev
    Next
    INDEX
    Explanations

    negative assertions or denials about existence, events, or desires

    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
    eÅŁ
    -0.07
    entai
    -0.07
    ýt
    -0.07
    Disposed
    -0.07
     Wheeler
    -0.07
    _trees
    -0.07
    /locale
    -0.07
    ãĤ¿ãĥ«
    -0.07
     FactoryBot
    -0.07
    fte
    -0.06
    POSITIVE LOGITS
     exist
    0.08
     existed
    0.07
     exists
    0.07
     Sherman
    0.07
    enda
    0.07
    _exist
    0.06
     existence
    0.06
    Ł
    0.06
    veau
    0.06
     yet
    0.06
    Activations Density 0.025%

    No Known Activations