© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 77993
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical and political designations

    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
     forget
    -0.06
    assel
    -0.06
     Sector
    -0.06
     spring
    -0.05
    ivant
    -0.05
    -p
    -0.05
     Schwe
    -0.05
    aud
    -0.05
    oes
    -0.05
     selfish
    -0.05
    POSITIVE LOGITS
    Concurrency
    0.08
     anomal
    0.08
    ller
    0.07
    -Cs
    0.07
    wner
    0.07
    _managed
    0.07
    uridad
    0.07
     //č↵
    0.07
     ê²
    0.07
    deen
    0.07
    Activations Density 0.004%

    No Known Activations