© 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. 29382
    Prev
    Next
    INDEX
    Explanations

    terms associated with political and administrative contexts

    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
    uyá»ħn
    -0.07
     CHUNK
    -0.07
    rewrite
    -0.07
    atica
    -0.07
     WithEvents
    -0.07
    uggy
    -0.07
    HING
    -0.07
    ocaust
    -0.06
    éric
    -0.06
     CHtml
    -0.06
    POSITIVE LOGITS
    580
    0.06
     record
    0.06
    evin
    0.06
    esel
    0.06
    996
    0.06
    583
    0.06
     history
    0.06
     career
    0.06
    errupted
    0.06
    973
    0.05
    Activations Density 0.011%

    No Known Activations