© 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. 83287
    Prev
    Next
    INDEX
    Explanations

    colons and their usage 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
    tries
    -0.07
    778
    -0.06
    awan
    -0.06
    να
    -0.06
    ernity
    -0.06
    ynchronously
    -0.06
    qb
    -0.06
    uden
    -0.06
    ength
    -0.06
     Bett
    -0.06
    POSITIVE LOGITS
     Tas
    0.07
    èĮ
    0.07
     Pole
    0.07
     polar
    0.06
     tas
    0.06
    nas
    0.06
    edelta
    0.06
     Plantae
    0.06
     Civil
    0.06
     Merc
    0.06
    Activations Density 0.001%

    No Known Activations