© 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. 77868
    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
    .INSTANCE
    -0.07
    rah
    -0.07
    åħĥ
    -0.07
     springfox
    -0.07
    erer
    -0.07
    cé
    -0.06
    chu
    -0.06
    olie
    -0.06
    /bower
    -0.06
    mund
    -0.06
    POSITIVE LOGITS
    .gr
    0.08
     Greek
    0.08
     Greece
    0.08
    ipsis
    0.07
    ÎĦ
    0.07
    akis
    0.07
    opoulos
    0.06
    ume
    0.06
    atak
    0.06
     Greeks
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.