© 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. 17-LLAMASCOPE-RES-131K
    11. 14950
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals' names and their titles or honorifics

    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
    ỹ
    -0.06
    agnar
    -0.06
    ovit
    -0.06
    hled
    -0.06
    orient
    -0.06
    ollar
    -0.06
    stype
    -0.06
    æ¡
    -0.06
    elda
    -0.05
     rest
    -0.05
    POSITIVE LOGITS
     ayrıca
    0.07
    ascus
    0.06
    çļĦä¸Ģ
    0.06
    ifa
    0.06
     Martinez
    0.06
    chwitz
    0.06
    306
    0.06
    ::$
    0.06
    prot
    0.06
    795
    0.06
    Activations Density 0.006%

    No Known Activations