© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 107212
    Prev
    Next
    INDEX
    Explanations

    phrases related to requirements and permissions in various contexts

    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
     chimney
    -0.06
    agnostic
    -0.06
    isel
    -0.06
    ep
    -0.06
    deen
    -0.06
    antan
    -0.06
     ApplicationException
    -0.06
    anka
    -0.06
    enson
    -0.06
    thed
    -0.06
    POSITIVE LOGITS
     possession
    0.09
     experience
    0.08
     knowledge
    0.08
    ré
    0.08
    okit
    0.07
     acquire
    0.07
     Experience
    0.06
     acquired
    0.06
     Buzz
    0.06
     ownership
    0.06
    Activations Density 0.053%

    No Known Activations