© 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. 126487
    Prev
    Next
    INDEX
    Explanations

    references to studies and researchers, particularly those leading research efforts

    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
    acco
    -0.07
    æ£
    -0.07
    ellan
    -0.07
    паÑĤ
    -0.07
    _Pin
    -0.07
    kola
    -0.06
    assa
    -0.06
    ventions
    -0.06
    illet
    -0.06
    SCI
    -0.06
    POSITIVE LOGITS
    roit
    0.06
     nhau
    0.06
    827
    0.06
    nod
    0.06
    ä¹ĭä¸Ģ
    0.06
    ·
    0.06
    ral
    0.06
    .ali
    0.06
    511
    0.06
    ırı
    0.06
    Activations Density 0.003%

    No Known Activations