© 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. 87388
    Prev
    Next
    INDEX
    Explanations

    phrases indicating service offerings and delivery options

    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
    ł
    -0.08
    ouver
    -0.08
     EÅŁ
    -0.07
    ì¼ĢìĿ´
    -0.07
    çŃĭ
    -0.07
    оÑģÑĤаÑĤ
    -0.07
    жд
    -0.07
    odate
    -0.07
    breaking
    -0.06
    اÙĨس
    -0.06
    POSITIVE LOGITS
    amat
    0.06
    ibal
    0.06
    imson
    0.06
    eteria
    0.06
    eyse
    0.06
     Chem
    0.06
    iben
    0.06
    rous
    0.06
    asha
    0.06
    yre
    0.05
    Activations Density 0.002%

    No Known Activations