© 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. 31105
    Prev
    Next
    INDEX
    Explanations

    phrases related to governance and political theory

    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
    aight
    -0.10
    oref
    -0.08
    rud
    -0.07
    åĩĨ
    -0.07
    OutOfBoundsException
    -0.07
    slideDown
    -0.07
     recycle
    -0.07
    ãģıãĤĵ
    -0.07
     conduc
    -0.07
    _VOID
    -0.07
    POSITIVE LOGITS
     implication
    0.09
     intent
    0.07
     /
    0.07
     plan
    0.07
     expectation
    0.07
     assumption
    0.07
     hope
    0.07
     intention
    0.06
     consensus
    0.06
     indications
    0.06
    Activations Density 0.049%

    No Known Activations