© 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. 74127
    Prev
    Next
    INDEX
    Explanations

    references to chronicles or chronological narratives

    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
    ularity
    -0.08
    æģ¯
    -0.07
    ucci
    -0.07
    ollar
    -0.07
    igo
    -0.06
    à¤Łà¤°
    -0.06
    ious
    -0.06
    erville
    -0.06
    /lib
    -0.06
    andan
    -0.06
    POSITIVE LOGITS
    ÚĨÙĩ
    0.07
    istically
    0.07
    emy
    0.07
    747
    0.07
    hound
    0.07
    ourcem
    0.07
    icle
    0.06
     Gad
    0.06
    ilig
    0.06
    urette
    0.06
    Activations Density 0.009%

    No Known Activations