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

    Neuronpedia

    Jacobian LensNEW
    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. 40593
    Prev
    Next
    INDEX
    Explanations

    content related to cost analysis and acquisition processes

    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
     mascul
    -0.07
    838
    -0.06
     Preconditions
    -0.06
    æ¨ĵ
    -0.06
    187
    -0.06
    ono
    -0.05
    kat
    -0.05
    https
    -0.05
    imet
    -0.05
     rej
    -0.05
    POSITIVE LOGITS
    оÑĤе
    0.07
    escort
    0.07
    edException
    0.07
    DEX
    0.07
    oji
    0.07
    oki
    0.07
    steller
    0.07
    outine
    0.07
    phinx
    0.07
    Escort
    0.07
    Activations Density 0.011%

    No Known Activations