© 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. 9-LLAMASCOPE-RES-131K
    11. 98256
    Prev
    Next
    INDEX
    Explanations

    references to mobile applications and their functionalities

    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
    atha
    -0.07
     Catch
    -0.06
     Lum
    -0.06
     Cir
    -0.06
     suspect
    -0.06
     Kale
    -0.06
    ffen
    -0.06
    å¢ĥ
    -0.06
     pass
    -0.06
    ãĥ¼ãĥ«ãĥī
    -0.05
    POSITIVE LOGITS
    âĢ¦.↵↵
    0.07
     tả
    0.07
    .openConnection
    0.07
    ForResource
    0.07
    appable
    0.07
     chá»īnh
    0.07
    mys
    0.06
    eten
    0.06
    _GP
    0.06
    447
    0.06
    Activations Density 0.013%

    No Known Activations