© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 61237
    Prev
    Next
    INDEX
    Explanations

    elements related to narrative perspective and character insights

    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
    ihan
    -0.07
    rung
    -0.07
    adol
    -0.07
    egl
    -0.07
    æ³Ľ
    -0.07
    mez
    -0.07
     Goth
    -0.06
    æŁĦ
    -0.06
     tube
    -0.06
    ategor
    -0.06
    POSITIVE LOGITS
    walls
    0.07
    omet
    0.06
     Walls
    0.06
     WCHAR
    0.06
     chapters
    0.06
    tsx
    0.06
    Ìī
    0.06
    lio
    0.06
    ili
    0.06
     describing
    0.06
    Activations Density 0.014%

    No Known Activations