© 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. 130520
    Prev
    Next
    INDEX
    Explanations

    various types of cake and their descriptions

    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
    wal
    -0.08
    ÑĢап
    -0.07
    icl
    -0.07
    опаÑģ
    -0.07
    éº
    -0.07
    dbus
    -0.07
    imore
    -0.07
    ubat
    -0.07
    .ravel
    -0.07
     пиÑĤ
    -0.07
    POSITIVE LOGITS
    798
    0.07
    671
    0.06
    via
    0.06
     shares
    0.06
     via
    0.06
    669
    0.06
     Wikimedia
    0.06
    ouch
    0.06
    OUCH
    0.06
    SHARE
    0.06
    Activations Density 0.003%

    No Known Activations