© 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. 39002
    Prev
    Next
    INDEX
    Explanations

    sentiments about storytelling in games and literature

    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
     Haz
    -0.07
    Ñīина
    -0.06
    OUNDS
    -0.06
     your
    -0.06
    ammer
    -0.06
    anja
    -0.06
    öz
    -0.06
    άÏĤ
    -0.06
     Kern
    -0.06
    ença
    -0.06
    POSITIVE LOGITS
     saya
    0.09
     myself
    0.08
    æĪij
    0.08
     tôi
    0.07
    pref
    0.07
     preference
    0.07
     sometimes
    0.07
     usually
    0.07
    Sometimes
    0.07
     kov
    0.07
    Activations Density 0.036%

    No Known Activations