© 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. 129664
    Prev
    Next
    INDEX
    Explanations

    words related to principles, particularly in academic or scientific contexts

    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
    optera
    -0.08
    342
    -0.07
    360
    -0.07
    cit
    -0.07
    igner
    -0.07
    897
    -0.07
    иÑĨ
    -0.06
    uchar
    -0.06
    uku
    -0.06
    macen
    -0.06
    POSITIVE LOGITS
    ippet
    0.07
    linger
    0.07
    oms
    0.07
    ABEL
    0.06
     Parade
    0.06
    SENT
    0.06
    yre
    0.06
     Sır
    0.06
    orado
    0.06
     omn
    0.06
    Activations Density 0.006%

    No Known Activations