© 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. 105974
    Prev
    Next
    INDEX
    Explanations

    references to acts or actions, particularly those that convey moral or ethical significance

    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
    gh
    -0.08
    ity
    -0.08
    celik
    -0.07
    icari
    -0.07
    Ú¯Ùĩ
    -0.07
    --------------------------------------------------------------------------↵
    -0.07
    lic
    -0.07
    loo
    -0.07
    plies
    -0.07
    lands
    -0.07
    POSITIVE LOGITS
     of
    0.08
     performed
    0.07
    Torrent
    0.07
    acts
    0.06
    INI
    0.06
    umin
    0.06
    /questions
    0.06
    inic
    0.06
    ings
    0.06
    348
    0.06
    Activations Density 0.008%

    No Known Activations