© 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. 18346
    Prev
    Next
    INDEX
    Explanations

    occurrences of possessive forms

    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
    à¹ģละส
    -0.07
    ÑĤÑı
    -0.06
    ØŃداث
    -0.06
    нез
    -0.06
    icens
    -0.06
     Kling
    -0.06
     coco
    -0.06
    ALAR
    -0.06
    oc
    -0.06
    .Interop
    -0.06
    POSITIVE LOGITS
     Revenge
    0.09
     Guide
    0.08
    -guide
    0.08
    aurus
    0.08
     Legacy
    0.07
     guide
    0.07
    Guide
    0.07
    isia
    0.07
    ITTER
    0.07
    pose
    0.06
    Activations Density 0.023%

    No Known Activations