© 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. 17-LLAMASCOPE-RES-131K
    6. 16037
    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
    vä
    -0.08
    agas
    -0.08
     Aydın
    -0.08
     Erotik
    -0.07
    avras
    -0.07
     dna
    -0.07
    lech
    -0.07
     ciz
    -0.07
    å¾ĭ
    -0.07
    etto
    -0.07
    POSITIVE LOGITS
    âĢİ
    0.07
     
    0.06
     -
    0.06
    oline
    0.06
     invaluable
    0.06
     incredibly
    0.06
     POLITICO
    0.06
     âĢİ
    0.06
    orn
    0.06
    stown
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.