© 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. 15-LLAMASCOPE-RES-131K
    11. 88119
    Prev
    Next
    INDEX
    Explanations

    phrases that convey decision-making and planning in sports contexts

    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
     himself
    -0.08
    urf
    -0.08
    ycl
    -0.07
    ìĽĥ
    -0.07
     Morm
    -0.07
    мини
    -0.07
    æĶ
    -0.07
    usters
    -0.07
     personally
    -0.07
    /activity
    -0.07
    POSITIVE LOGITS
     him
    0.10
     Hick
    0.07
     onu
    0.06
     그를
    0.06
     treat
    0.06
     draft
    0.06
     lui
    0.06
     send
    0.06
    éĢģ
    0.06
    enci
    0.06
    Activations Density 0.053%

    No Known Activations