© 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. 127487
    Prev
    Next
    INDEX
    Explanations

    references to authors and their associated works

    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
    isoft
    -0.08
    EDIA
    -0.07
    oft
    -0.06
    áš
    -0.06
     treff
    -0.06
    pedia
    -0.06
    ¼åIJĪ
    -0.06
    iu
    -0.06
    ault
    -0.06
    çļĦå°ı
    -0.06
    POSITIVE LOGITS
     anon
    0.09
    ospace
    0.07
     unidentified
    0.07
     Various
    0.06
    steder
    0.06
     Robert
    0.06
    .AutoSizeMode
    0.06
    ضاÙĨ
    0.06
    ãĥ¡ãĥ³ãĥĪ
    0.06
     Anonymous
    0.06
    Activations Density 0.043%

    No Known Activations