© 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. 54105
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty and speculation about individuals or situations

    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
    illian
    -0.08
    zk
    -0.08
    chine
    -0.07
    canf
    -0.07
    aldo
    -0.07
    avery
    -0.07
    ENO
    -0.07
    å¦Ļ
    -0.07
    kö
    -0.07
    iri
    -0.07
    POSITIVE LOGITS
     meant
    0.06
     intention
    0.06
    _SLAVE
    0.06
     dim
    0.06
     Implicit
    0.06
     intend
    0.05
    .getRow
    0.05
     ↵
    0.05
     felt
    0.05
     intended
    0.05
    Activations Density 0.048%

    No Known Activations