© 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. 83079
    Prev
    Next
    INDEX
    Explanations

    phrases and symbols related to measurements and quantities

    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
    оÑĢе
    -0.07
    Raw
    -0.07
     дол
    -0.07
    ÏģοÏį
    -0.06
    CCCCCC
    -0.06
    деÑĤ
    -0.06
    èle
    -0.06
    ROKE
    -0.06
    itelist
    -0.06
    lei
    -0.06
    POSITIVE LOGITS
    onaut
    0.08
    iba
    0.07
     unp
    0.06
     Uint
    0.06
     backlog
    0.06
     carbon
    0.06
    ún
    0.06
    isode
    0.06
     seamless
    0.06
    istributed
    0.06
    Activations Density 0.003%

    No Known Activations