© 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. 62636
    Prev
    Next
    INDEX
    Explanations

    terms related to dominance and prevailing conditions or beliefs

    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
    gb
    -0.07
    other
    -0.07
    ãģ¨ãģį
    -0.06
    sc
    -0.06
    ed
    -0.06
    off
    -0.06
    alle
    -0.06
    rev
    -0.06
    assin
    -0.06
    .uni
    -0.06
    POSITIVE LOGITS
    /current
    0.08
    ently
    0.08
    ActionCode
    0.08
    antly
    0.07
    ance
    0.07
    ances
    0.07
    ingly
    0.07
    ence
    0.07
    ÐĤ
    0.07
    .scalablytyped
    0.07
    Activations Density 0.005%

    No Known Activations