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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 119125
    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
       
    -0.07
    ÃĬ
    -0.06
      
    -0.06
    qa
    -0.06
    asure
    -0.06
    edik
    -0.06
     
    -0.06
     secondary
    -0.05
     manufacturer
    -0.05
    ifu
    -0.05
    POSITIVE LOGITS
    icerca
    0.08
    вано
    0.08
     kå
    0.08
    .Tab
    0.08
    ÐIJÑĢÑħÑĸв
    0.07
    ÑĤÑİ
    0.07
    ongyang
    0.07
     Caucus
    0.07
    orners
    0.07
    ukkan
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.