© 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. 130340
    Prev
    Next
    INDEX
    Explanations

    instructions related to installing and navigating software

    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
    ercul
    -0.07
     sav
    -0.07
    æĮ¯ãĤĬ
    -0.06
    BILE
    -0.06
    hof
    -0.06
    ikan
    -0.06
    .rev
    -0.06
     Bulk
    -0.06
     Sav
    -0.06
     PIO
    -0.06
    POSITIVE LOGITS
    criptors
    0.07
    antry
    0.07
    ackers
    0.07
    æ°ı
    0.06
    picker
    0.06
    èĶµ
    0.06
    arty
    0.06
    burger
    0.06
    omit
    0.06
     Georg
    0.06
    Activations Density 0.001%

    No Known Activations