© 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. 107321
    Prev
    Next
    INDEX
    Explanations

    phrases related to government and economy

    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
    "crypto
    -0.08
    urses
    -0.06
     Mine
    -0.06
    334
    -0.06
     piv
    -0.06
    /latest
    -0.06
    indow
    -0.06
     twin
    -0.06
    skirts
    -0.06
    gos
    -0.06
    POSITIVE LOGITS
    anten
    0.07
    inker
    0.07
    lag
    0.07
    ehr
    0.06
    ìĤ
    0.06
    éĻµ
    0.06
    reinterpret
    0.06
    evin
    0.06
    #ad
    0.06
     propor
    0.06
    Activations Density 0.001%

    No Known Activations