© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 129552
    Prev
    Next
    INDEX
    Explanations

    elements related to planning and organization in various contexts

    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
    VES
    -0.06
    سÙĪ
    -0.06
    /grpc
    -0.06
    olie
    -0.06
    URT
    -0.05
    andy
    -0.05
     yerini
    -0.05
    baÅŁ
    -0.05
     Vas
    -0.05
    ideos
    -0.05
    POSITIVE LOGITS
    kest
    0.08
     fres
    0.07
     opportunity
    0.07
    ERO
    0.07
    PyObject
    0.07
    lando
    0.07
    Mathf
    0.07
    avin
    0.07
    ÃŃg
    0.06
    ุà¸Ĺ
    0.06
    Activations Density 0.026%

    No Known Activations