© 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. 70188
    Prev
    Next
    INDEX
    Explanations

    phrases related to political control and party dynamics

    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
    .opensource
    -0.08
    λοÏħ
    -0.07
    .Binding
    -0.07
     DefaultValue
    -0.07
    åħ·
    -0.07
     ç±
    -0.07
    úÄįast
    -0.07
    iggins
    -0.07
    arak
    -0.06
    roat
    -0.06
    POSITIVE LOGITS
     prive
    0.07
    DataProvider
    0.07
    .assertj
    0.06
     flipping
    0.06
    control
    0.06
    Priv
    0.06
     privilege
    0.06
     seats
    0.06
     likely
    0.06
     minority
    0.06
    Activations Density 0.012%

    No Known Activations