© 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. 27646
    Prev
    Next
    INDEX
    Explanations

    transitional and contextual phrases that indicate logical connections in a narrative

    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
    abay
    -0.07
     fisse
    -0.07
    _TUN
    -0.07
     bana
    -0.07
    üz
    -0.07
     doz
    -0.07
    egl
    -0.07
    imonial
    -0.07
    RuntimeObject
    -0.07
     æ¢
    -0.07
    POSITIVE LOGITS
     cal
    0.08
    ody
    0.07
    eros
    0.06
    ERO
    0.06
     fur
    0.06
    jer
    0.06
     dev
    0.06
    vant
    0.06
    ero
    0.06
    Âł
    0.06
    Activations Density 0.003%

    No Known Activations