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

    Neuronpedia

    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. 105786
    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
     Companion
    -0.06
    inned
    -0.06
    itu
    -0.06
    ike
    -0.06
    Ordered
    -0.06
    azen
    -0.06
    argo
    -0.06
    å®
    -0.06
     strings
    -0.06
    onic
    -0.05
    POSITIVE LOGITS
    SOR
    0.08
     GOODMAN
    0.07
    ovie
    0.07
    ạn
    0.07
    ãĥĨãĥ«
    0.07
    hos
    0.07
    zÄħd
    0.07
    dad
    0.07
    vos
    0.07
    metros
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.