© 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. 71247
    Prev
    Next
    INDEX
    Explanations

    phrases indicating restrictions or limitations in communication

    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
    eyin
    -0.07
    zano
    -0.07
    argin
    -0.07
     seins
    -0.07
    ãģ¤ãģij
    -0.07
    zim
    -0.06
    ä¹³
    -0.06
    ccion
    -0.06
    ãģıãģł
    -0.06
    ãģ¤ãģ¶
    -0.06
    POSITIVE LOGITS
     publicly
    0.07
    ussen
    0.07
     freely
    0.07
    ucher
    0.07
    nap
    0.06
    ccount
    0.06
     quot
    0.06
     ÑģамоÑģÑĤ
    0.06
     Bale
    0.06
     Gus
    0.06
    Activations Density 0.001%

    No Known Activations