© 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. 9-LLAMASCOPE-RES-131K
    11. 97063
    Prev
    Next
    INDEX
    Explanations

    references to rugs and their related characteristics

    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
    sou
    -0.07
    åijĺ
    -0.06
    uggage
    -0.06
     rigorous
    -0.06
    act
    -0.06
    rud
    -0.06
    payload
    -0.06
    ument
    -0.06
    s
    -0.06
     rigor
    -0.06
    POSITIVE LOGITS
    .Widget
    0.07
    STANCE
    0.07
    ÑģÑĤи
    0.07
    á»Ļ
    0.07
    SPATH
    0.06
    ÄĽn
    0.06
    agements
    0.06
    SqlServer
    0.06
    ccb
    0.06
    ãĥ¼ãĤ¯
    0.06
    Activations Density 0.003%

    No Known Activations