© 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. 31099
    Prev
    Next
    INDEX
    Explanations

    narrative elements related to the creation and development of characters or stories

    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
    agem
    -0.05
    olin
    -0.05
    DebugEnabled
    -0.05
    izu
    -0.05
    æŁĶ
    -0.05
    endid
    -0.05
    Preview
    -0.05
    agna
    -0.05
    iz
    -0.05
    (Runtime
    -0.05
    POSITIVE LOGITS
     actual
    0.19
    æŃ£å¼ı
    0.19
     full
    0.17
     further
    0.16
    actual
    0.16
     formal
    0.15
    羣æŃ£
    0.15
     official
    0.15
     officially
    0.14
     Actual
    0.14
    Activations Density 0.225%

    No Known Activations