© 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 EvalsExportsinterp-engineNEWAPI 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. 98806
    Prev
    Next
    INDEX
    Explanations

    negative descriptors or references to obstacles and challenges

    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
    eriod
    -0.07
    .tt
    -0.07
    amation
    -0.07
     Yer
    -0.06
    ripp
    -0.06
    illery
    -0.06
    ourage
    -0.06
    opi
    -0.06
     Hier
    -0.06
    Hier
    -0.06
    POSITIVE LOGITS
    erval
    0.06
    æĦı
    0.06
     wed
    0.06
     lorem
    0.06
    hd
    0.06
    ê°Ŀ
    0.06
    921
    0.06
    _callable
    0.06
     mét
    0.06
     wedge
    0.06
    Activations Density 0.017%

    No Known Activations