© 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. 126624
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements and structure

    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
    raç
    -0.06
     Martinez
    -0.06
    ammad
    -0.06
    ListOf
    -0.06
    quez
    -0.05
    onga
    -0.05
     fing
    -0.05
    aston
    -0.05
    ase
    -0.05
    :UITableView
    -0.05
    POSITIVE LOGITS
    IRR
    0.07
    cgi
    0.07
    rosse
    0.07
    иной
    0.07
    /TT
    0.07
    ιαÏĤ
    0.06
    GetInstance
    0.06
    lef
    0.06
    ãĥĭãĥ¼
    0.06
    _helpers
    0.06
    Activations Density 0.003%

    No Known Activations