© 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. 126186
    Prev
    Next
    INDEX
    Explanations

    phrases related to guidance and future trends

    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
    uvo
    -0.07
    urr
    -0.07
    InBackground
    -0.07
    erten
    -0.06
    ä¸
    -0.06
    íıIJ
    -0.06
    aley
    -0.06
    obic
    -0.06
    ovice
    -0.06
    ple
    -0.06
    POSITIVE LOGITS
     direction
    0.21
     directions
    0.18
    direction
    0.17
    æĸ¹åIJij
    0.17
     Direction
    0.16
    -direction
    0.15
     Directions
    0.14
    Direction
    0.13
    .direction
    0.13
    _direction
    0.13
    Activations Density 0.078%

    No Known Activations