© 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. 56090
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to leadership and authority positions

    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
    anca
    -0.07
    oler
    -0.07
    أس
    -0.07
    eden
    -0.07
    -pane
    -0.07
    kich
    -0.07
    zell
    -0.07
    ikan
    -0.07
    ober
    -0.07
    ense
    -0.07
    POSITIVE LOGITS
     of
    0.07
    WebResponse
    0.06
    itä
    0.06
    uÄį
    0.06
    apur
    0.06
    inha
    0.06
    -ı
    0.06
    åħ¼
    0.06
    azar
    0.05
     Hin
    0.05
    Activations Density 0.025%

    No Known Activations