© 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. 78450
    Prev
    Next
    INDEX
    Explanations

    numeric references pertaining to dates and statistics

    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
     touch
    -0.06
    628
    -0.06
     Touch
    -0.05
    義
    -0.05
    lying
    -0.05
     Mercy
    -0.05
    obot
    -0.05
    istani
    -0.05
    Touch
    -0.05
    arian
    -0.05
    POSITIVE LOGITS
     limburg
    0.07
    edn
    0.07
    forman
    0.07
    eyse
    0.07
    ocker
    0.07
    obuf
    0.07
    tach
    0.07
    edir
    0.07
    _firestore
    0.07
    ILED
    0.07
    Activations Density 0.002%

    No Known Activations