© 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. 72027
    Prev
    Next
    INDEX
    Explanations

    phrases indicating effort, ambition, and commitment to improvement or growth

    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
    /from
    -0.07
     dikke
    -0.07
    mun
    -0.07
    atee
    -0.06
    ne
    -0.06
    /or
    -0.06
    ovel
    -0.06
    quier
    -0.06
    weg
    -0.06
    lid
    -0.06
    POSITIVE LOGITS
    /testify
    0.08
    lessly
    0.08
     toward
    0.07
    CppClass
    0.07
     Gol
    0.07
    ieve
    0.07
    Balance
    0.07
     towards
    0.07
    leich
    0.07
     balance
    0.07
    Activations Density 0.004%

    No Known Activations