© 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. 40437
    Prev
    Next
    INDEX
    Explanations

    specific locations, cultural references, and prominent figures in artistic 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
     Wo
    -0.07
    legg
    -0.06
    ómo
    -0.06
     hod
    -0.06
    uzzi
    -0.06
    agn
    -0.06
     and
    -0.06
    pend
    -0.06
    uro
    -0.06
     pat
    -0.06
    POSITIVE LOGITS
     ÑĢеÑģп
    0.07
    neh
    0.07
    ượt
    0.06
     alternatively
    0.06
    ForObject
    0.06
    isto
    0.06
    .setTo
    0.06
    UIScreen
    0.06
    eczy
    0.06
     anlamına
    0.06
    Activations Density 0.018%

    No Known Activations