© 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 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. 17-LLAMASCOPE-RES-131K
    11. 118699
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or the presence of items within a context

    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
    timeofday
    -0.09
     èĩ
    -0.07
    FAULT
    -0.07
    vÄĽ
    -0.07
    ollapsed
    -0.07
    vier
    -0.07
    ourg
    -0.07
    extView
    -0.07
    ixed
    -0.07
    ovenant
    -0.07
    POSITIVE LOGITS
    oter
    0.08
    kw
    0.07
    opy
    0.07
    309
    0.06
    owski
    0.06
    ActionTypes
    0.06
    TouchUpInside
    0.06
    SB
    0.06
     since
    0.06
    unden
    0.05
    Activations Density 0.000%

    No Known Activations