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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 130259
    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
     براÙī
    -0.08
    Ùī
    -0.08
    GenerationStrategy
    -0.07
    asso
    -0.07
    олн
    -0.07
    arası
    -0.07
    ÅĤad
    -0.07
    amac
    -0.07
    tres
    -0.07
    InParameter
    -0.07
    POSITIVE LOGITS
    obby
    0.06
    roman
    0.06
     /
    0.06
     ZIP
    0.06
    кÑĥп
    0.06
    ypi
    0.06
     prem
    0.05
     COVID
    0.05
     Similar
    0.05
     idle
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.