© 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. 128832
    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
    ubi
    -0.07
     budd
    -0.07
    displayText
    -0.07
    etik
    -0.07
    EEP
    -0.06
    ijken
    -0.06
     -*
    -0.06
    isas
    -0.06
     shadow
    -0.06
     túi
    -0.06
    POSITIVE LOGITS
    .onOptionsItemSelected
    0.06
    -toolbar
    0.06
    antly
    0.06
     ë¿IJ
    0.05
    grily
    0.05
    ubby
    0.05
    oker
    0.05
    alsa
    0.05
    igure
    0.05
     Wing
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.