© 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 EvalsExportsinterp-engineNEWAPI 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. 69625
    Prev
    Next
    INDEX
    Explanations

    references to official reports and government-related activities

    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
     Announcement
    -0.08
    eft
    -0.07
     annunci
    -0.07
     annonce
    -0.07
     announcement
    -0.07
    asser
    -0.07
     minh
    -0.07
    ytt
    -0.07
    ercial
    -0.06
    enser
    -0.06
    POSITIVE LOGITS
     internal
    0.10
    internal
    0.09
     Internal
    0.09
    Internal
    0.09
     внÑĥÑĤÑĢен
    0.08
    åĨħéĥ¨
    0.08
     INTERNAL
    0.08
    _INTERNAL
    0.08
     document
    0.07
    /Internal
    0.07
    Activations Density 0.016%

    No Known Activations