© 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. 5-LLAMASCOPE-RES-131K
    11. 125757
    Prev
    Next
    INDEX
    Explanations

    words related to educational institutions and their operational aspects

    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
    .mongodb
    -0.06
    ese
    -0.06
    arms
    -0.06
    umbs
    -0.06
    verture
    -0.06
    VILLE
    -0.06
    SHARE
    -0.06
     indeb
    -0.06
    insk
    -0.06
    lop
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.07
    cess
    0.06
    trap
    0.06
    ominator
    0.06
     bóng
    0.06
     Lyon
    0.06
    WithOptions
    0.06
    HN
    0.06
    zon
    0.06
    raud
    0.06
    Activations Density 0.000%

    No Known Activations