© 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. 9-LLAMASCOPE-RES-131K
    11. 95325
    Prev
    Next
    INDEX
    Explanations

    phrases related to project evaluation and assessment processes

    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
    eya
    -0.08
    ickerView
    -0.08
    ETERS
    -0.07
    kers
    -0.07
    ìĦĿ
    -0.07
    adero
    -0.07
    .qml
    -0.06
    _DIAG
    -0.06
    епÑĤи
    -0.06
    eters
    -0.06
    POSITIVE LOGITS
    ç®
    0.06
    æĸĩåĮĸ
    0.06
     Transit
    0.06
    ale
    0.06
    ¼åIJĪ
    0.06
     Alex
    0.06
    UR
    0.06
    icult
    0.05
    ove
    0.05
    .getExternal
    0.05
    Activations Density 0.024%

    No Known Activations