© 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. 17-LLAMASCOPE-RES-131K
    11. 85798
    Prev
    Next
    INDEX
    Explanations

    questions regarding creative processes and techniques

    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
     rendition
    -0.06
     diversion
    -0.06
    achi
    -0.06
    quip
    -0.06
     Morrow
    -0.06
    rosse
    -0.06
    /sweetalert
    -0.06
    rani
    -0.05
    éd
    -0.05
    ija
    -0.05
    POSITIVE LOGITS
     usually
    0.09
    usually
    0.09
    Usually
    0.08
     sometimes
    0.08
     Usually
    0.07
    仲
    0.07
    sometimes
    0.07
    process
    0.07
     задов
    0.07
     often
    0.07
    Activations Density 0.045%

    No Known Activations