© 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 EvalsExportsinterp-engineNEWAPI 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. 117361
    Prev
    Next
    INDEX
    Explanations

    HTML tags and related syntax elements

    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
    uffle
    -0.07
    ork
    -0.06
    rove
    -0.06
     progen
    -0.06
    agli
    -0.06
    è£ľ
    -0.06
     Gratuit
    -0.06
    chia
    -0.06
     Maz
    -0.06
    tring
    -0.05
    POSITIVE LOGITS
    imdi
    0.07
    _intro
    0.07
    имÑĥ
    0.07
    ifr
    0.06
    бÑĥдÑĮ
    0.06
    urement
    0.06
    fung
    0.06
    óm
    0.06
     dealloc
    0.06
    ument
    0.06
    Activations Density 0.003%

    No Known Activations