© 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. 74172
    Prev
    Next
    INDEX
    Explanations

    adjectives that convey improvement or positive attributes

    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
    rame
    -0.07
    ilarity
    -0.07
     EÅŁ
    -0.07
    ino
    -0.06
    laughter
    -0.06
     dán
    -0.06
     Mayor
    -0.06
    quo
    -0.06
    py
    -0.06
    ugi
    -0.06
    POSITIVE LOGITS
     пÑĥÑĤем
    0.07
    ãģĶãģĸ
    0.07
     möglich
    0.07
    erais
    0.07
     ÑĪлÑıÑħом
    0.06
    bows
    0.06
    inish
    0.06
     thereby
    0.06
    781
    0.06
    izard
    0.06
    Activations Density 0.029%

    No Known Activations