© 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. 16043
    Prev
    Next
    INDEX
    Explanations

    references to rare-earth metals and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     æµĻæ±Ł
    -0.07
    izzo
    -0.07
    izona
    -0.07
    #
    -0.07
     Delta
    -0.07
    roti
    -0.06
    -caret
    -0.06
    rut
    -0.06
    omid
    -0.06
     Venez
    -0.06
    POSITIVE LOGITS
     Locked
    0.07
    umba
    0.07
    .ht
    0.07
    Rare
    0.07
    ium
    0.07
    (Cs
    0.07
     Spoon
    0.07
     element
    0.07
     Charge
    0.06
     rare
    0.06
    Activations Density 0.006%

    No Known Activations