© 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. 14666
    Prev
    Next
    INDEX
    Explanations

    language related to political power dynamics and affiliations

    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
    utters
    -0.07
     HEIGHT
    -0.07
     HOST
    -0.06
     anarchists
    -0.06
    aller
    -0.06
     teammate
    -0.06
    åĵį
    -0.06
    AINER
    -0.06
    TestingModule
    -0.06
    TING
    -0.06
    POSITIVE LOGITS
     appointments
    0.12
     positions
    0.11
     appointment
    0.09
     cabinet
    0.09
    positions
    0.09
     key
    0.08
     Positions
    0.08
     Cabinet
    0.08
     appoint
    0.08
     slots
    0.08
    Activations Density 0.047%

    No Known Activations