© 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. 130816
    Prev
    Next
    INDEX
    Explanations

    references to leadership and commands within organizations or groups

    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
    deen
    -0.10
    erule
    -0.09
    alis
    -0.09
    chemy
    -0.09
     ActiveForm
    -0.08
    dıģında
    -0.08
    VERRIDE
    -0.08
    alem
    -0.08
    RuntimeObject
    -0.08
    UILD
    -0.08
    POSITIVE LOGITS
     lead
    0.08
     Professor
    0.07
     experienced
    0.07
     “
    0.07
     its
    0.06
    à¥įबर
    0.06
     seasoned
    0.06
     Lead
    0.06
     master
    0.06
     ^
    0.06
    Activations Density 0.027%

    No Known Activations