© 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. 106682
    Prev
    Next
    INDEX
    Explanations

    dates and deadlines related to events and submissions

    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
    StackNavigator
    -0.07
    æĿIJ
    -0.07
    ataka
    -0.07
    æ£Ĵ
    -0.06
     svens
    -0.06
    екаÑĢ
    -0.06
    _AURA
    -0.06
    oftware
    -0.06
    OTO
    -0.06
    emek
    -0.06
    POSITIVE LOGITS
    isman
    0.07
    ÑģÑĭ
    0.07
    dash
    0.07
     dash
    0.07
    asser
    0.06
    äll
    0.06
    agal
    0.06
     Hum
    0.06
    ampie
    0.06
     Borg
    0.06
    Activations Density 0.006%

    No Known Activations