© 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. 76559
    Prev
    Next
    INDEX
    Explanations

    information related to events and cultural initiatives

    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
    iali
    -0.07
    Prefs
    -0.07
    atak
    -0.07
    alis
    -0.07
    ÇIJ
    -0.06
    onda
    -0.06
    REDENTIAL
    -0.06
    éné
    -0.06
    UpdateTime
    -0.06
     Wade
    -0.06
    POSITIVE LOGITS
     municip
    0.07
    å·
    0.06
    VD
    0.06
    ometown
    0.06
    elm
    0.06
    itet
    0.06
     žen
    0.06
    orden
    0.06
    District
    0.06
    _literals
    0.06
    Activations Density 0.007%

    No Known Activations