© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 4013
    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
    è§Ħå®ļ
    -0.07
    ecimal
    -0.07
    scenario
    -0.06
    Granted
    -0.06
    omid
    -0.06
    loub
    -0.06
    ิส
    -0.06
    ÑĢеб
    -0.06
    erty
    -0.06
    év
    -0.06
    POSITIVE LOGITS
     often
    0.07
    ï¸ı
    0.06
     expert
    0.06
    elly
    0.06
     perhaps
    0.06
     treatment
    0.06
     Expert
    0.06
    ør
    0.06
     machine
    0.06
    ning
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.