© 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. 15-LLAMASCOPE-RES-131K
    11. 61259
    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
    ete
    -0.07
    寸
    -0.07
    cate
    -0.07
    antha
    -0.06
    oter
    -0.06
    cpt
    -0.06
    oftware
    -0.06
    toJson
    -0.06
    /modal
    -0.06
    cak
    -0.06
    POSITIVE LOGITS
    stra
    0.06
    TRIES
    0.06
     thoát
    0.06
    eneg
    0.06
    ojis
    0.06
     Bry
    0.06
     reife
    0.05
     ön
    0.05
     DIR
    0.05
    0
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.