© 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. 126672
    Prev
    Next
    INDEX
    Explanations

    terminology related to cycling and bicycle infrastructure

    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
     depress
    -0.06
    akah
    -0.06
     bott
    -0.06
    ness
    -0.06
    succ
    -0.06
    Ú
    -0.06
     Chim
    -0.06
     Bans
    -0.06
    aml
    -0.05
    íģ¼
    -0.05
    POSITIVE LOGITS
    ุม
    0.07
     пÑĢеÑģÑĤ
    0.07
    peer
    0.07
    inte
    0.07
    .visitMethod
    0.07
    _FWD
    0.06
    anter
    0.06
    vÄĽÅĻ
    0.06
    RAIN
    0.06
    visor
    0.06
    Activations Density 0.004%

    No Known Activations