© 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. 79316
    Prev
    Next
    INDEX
    Explanations

    references to "inner" and its various contextual uses, particularly in relation to urban environments and communities

    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
    iec
    -0.08
    sdale
    -0.08
    alendar
    -0.08
    sch
    -0.08
    erdale
    -0.08
    epam
    -0.08
    ια
    -0.07
    ëĥ¥
    -0.07
    rå
    -0.07
    пÑĸд
    -0.07
    POSITIVE LOGITS
    most
    0.19
    halb
    0.10
    -most
    0.09
    -inner
    0.09
    MOST
    0.08
     most
    0.08
    anging
    0.08
    ings
    0.07
    est
    0.07
    esting
    0.07
    Activations Density 0.012%

    No Known Activations