© 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. 88810
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the basis or foundation of decisions and plans

    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
    ÄIJT
    -0.07
    Agent
    -0.07
    ɵ
    -0.07
    QE
    -0.07
    ãģ¨ãĤĤ
    -0.07
    adro
    -0.07
    .hom
    -0.07
    ëĮ
    -0.07
    Å¡enÃŃ
    -0.07
    aise
    -0.07
    POSITIVE LOGITS
     needs
    0.07
     principles
    0.07
     current
    0.07
     audience
    0.07
     principle
    0.07
     best
    0.06
     priorities
    0.06
     modern
    0.06
     their
    0.06
     our
    0.06
    Activations Density 0.019%

    No Known Activations