© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89314
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Guild
    -0.06
    _fmt
    -0.06
     card
    -0.06
    527
    -0.06
    Ư
    -0.06
    дÑĢом
    -0.05
    عب
    -0.05
    å¾
    -0.05
     Keeper
    -0.05
    Ưá»
    -0.05
    POSITIVE LOGITS
    ursal
    0.08
    ysi
    0.08
    ums
    0.07
    osi
    0.07
    laÄį
    0.07
    rej
    0.07
    ilog
    0.07
    ollo
    0.07
    langs
    0.07
    -parse
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.