© 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. 57331
    Prev
    Next
    INDEX
    Explanations

    numerical data related to protein composition and structure

    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
    ÑĢоб
    -0.07
     bach
    -0.06
    /includes
    -0.06
    berger
    -0.06
    idon
    -0.06
    اضر
    -0.06
    obra
    -0.06
    åł¡
    -0.06
    roud
    -0.06
    gable
    -0.06
    POSITIVE LOGITS
    ł
    0.07
    éré
    0.06
     Sai
    0.06
    apgolly
    0.06
    getAs
    0.06
    142
    0.06
     pul
    0.06
    ãĤ·ãĥ¼
    0.06
    tern
    0.06
    nesc
    0.06
    Activations Density 0.005%

    No Known Activations