© 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. 9-LLAMASCOPE-RES-131K
    11. 97257
    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
    lap
    -0.07
    ÑĤап
    -0.07
    ment
    -0.07
     needle
    -0.06
    riv
    -0.06
    çķ
    -0.06
    bert
    -0.06
    iete
    -0.06
    먹
    -0.06
     Thế
    -0.06
    POSITIVE LOGITS
    atham
    0.06
     cach
    0.06
     Vere
    0.06
    ElementException
    0.06
    erce
    0.06
    uguay
    0.06
     volley
    0.06
     Grape
    0.06
    aler
    0.06
     addCriterion
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.