© 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. 93778
    Prev
    Next
    INDEX
    Explanations

    numeric data or codes within the text

    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
    باش
    -0.06
    gebn
    -0.06
    åľ¨åľ°
    -0.06
    ryptography
    -0.06
    llib
    -0.06
    gest
    -0.06
    lok
    -0.06
    asic
    -0.06
    prites
    -0.06
    нок
    -0.06
    POSITIVE LOGITS
    lant
    0.06
    akin
    0.06
    aged
    0.06
     lect
    0.06
     backing
    0.06
    azon
    0.06
     MyApp
    0.06
    .gb
    0.06
     Evil
    0.06
     Saved
    0.06
    Activations Density 0.007%

    No Known Activations