© 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. 29020
    Prev
    Next
    INDEX
    Explanations

    phrases indicating specific groups or quantities

    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
    roc
    -0.08
    ovol
    -0.07
    bol
    -0.06
    елÑĮно
    -0.06
    ubl
    -0.06
    ÑĦоÑĢ
    -0.06
    ci
    -0.06
    sson
    -0.06
    arts
    -0.06
    sg
    -0.06
    POSITIVE LOGITS
    hek
    0.07
    odo
    0.07
     graded
    0.07
    itus
    0.06
    Them
    0.06
     Them
    0.06
    maal
    0.06
    iasi
    0.06
    peak
    0.06
    æ´¥
    0.06
    Activations Density 0.022%

    No Known Activations