© 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. 128485
    Prev
    Next
    INDEX
    Explanations

    issues related to governance and public administration challenges

    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
     Interracial
    -0.06
    heit
    -0.06
    hots
    -0.06
    leme
    -0.06
    uar
    -0.06
    ophil
    -0.06
     qc
    -0.06
     Insecta
    -0.06
    isini
    -0.06
     GOODMAN
    -0.06
    POSITIVE LOGITS
     political
    0.07
     imported
    0.06
    hawk
    0.06
     foreign
    0.06
     Imported
    0.06
     imports
    0.06
     Imports
    0.06
    alc
    0.06
    TERN
    0.05
     sex
    0.05
    Activations Density 0.043%

    No Known Activations