© 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. 553
    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
    ernet
    -0.08
    ensen
    -0.06
    essen
    -0.06
     -:-
    -0.06
    ModelProperty
    -0.06
    ERM
    -0.06
    licer
    -0.06
    esub
    -0.06
    reau
    -0.06
    ï¿
    -0.06
    POSITIVE LOGITS
    Äĥr
    0.07
    adr
    0.06
    rans
    0.06
    rieved
    0.06
    admin
    0.06
    entarios
    0.06
     Campos
    0.06
    ulla
    0.06
    ÑĭÑĪ
    0.06
    ÑĢан
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.