© 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 EvalsExportsinterp-engineNEWAPI 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. 123771
    Prev
    Next
    INDEX
    Explanations

    discussions related to implications and nuances of practices 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
     Bare
    -0.07
    ære
    -0.06
    .dynamic
    -0.06
    nÃŃ
    -0.06
     creampie
    -0.06
    rol
    -0.06
    bare
    -0.06
    yas
    -0.06
    adir
    -0.06
     облиÑĩ
    -0.06
    POSITIVE LOGITS
     non
    0.24
     beyond
    0.24
     outside
    0.22
     other
    0.21
    éĿŀ
    0.20
    以å¤ĸ
    0.20
     Beyond
    0.19
    éĻ¤äºĨ
    0.19
     besides
    0.19
     Non
    0.18
    Activations Density 0.394%

    No Known Activations