© 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. 106288
    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
    .social
    -0.06
    iaux
    -0.06
    738
    -0.06
    licos
    -0.06
    emente
    -0.06
    ileÅŁ
    -0.06
    rien
    -0.06
    ancial
    -0.06
    arna
    -0.06
    cü
    -0.06
    POSITIVE LOGITS
    .crm
    0.07
    adil
    0.06
    jos
    0.06
     scraps
    0.06
     Grand
    0.06
    azel
    0.06
    vae
    0.06
     Magic
    0.06
    ìĬĪ
    0.06
     Final
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.