Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4487
    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
     âĸĪ
    -0.06
    ıs
    -0.06
    earer
    -0.06
    RICT
    -0.06
    vl
    -0.06
    رÙĩ
    -0.06
     recieved
    -0.06
    OutOfBoundsException
    -0.06
     clearfix
    -0.05
    igar
    -0.05
    POSITIVE LOGITS
    .opensource
    0.08
    ollider
    0.07
     EXEMPLARY
    0.07
    alte
    0.06
    omo
    0.06
    ADVERTISEMENT
    0.06
    manship
    0.06
    reff
    0.06
    incl
    0.06
     onDataChange
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.