© 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. 17319
    Prev
    Next
    INDEX
    Explanations

    phrases related to product packaging and features

    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
    asto
    -0.07
    бин
    -0.06
    565
    -0.06
    ainless
    -0.06
    iams
    -0.06
    croft
    -0.06
    celik
    -0.06
    аÑĤок
    -0.06
    ProgressHUD
    -0.06
    ewire
    -0.06
    POSITIVE LOGITS
     package
    0.08
     format
    0.08
     Geh
    0.07
    ailable
    0.07
    _packages
    0.07
    vrier
    0.07
    format
    0.07
     nutshell
    0.07
     khung
    0.07
    -package
    0.07
    Activations Density 0.011%

    No Known Activations