© 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. 85032
    Prev
    Next
    INDEX
    Explanations

    terms related to historical structures and their modifications

    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
    hlas
    -0.07
    çĸĨ
    -0.07
    ucha
    -0.07
    ÏĥÏĦα
    -0.07
    unik
    -0.07
    isas
    -0.06
     Zug
    -0.06
    едÑĮ
    -0.06
    amo
    -0.06
    %A
    -0.06
    POSITIVE LOGITS
     years
    0.09
    198
    0.08
    196
    0.07
     decades
    0.07
    195
    0.07
     recent
    0.07
    194
    0.07
    年代
    0.07
     modern
    0.07
     decade
    0.07
    Activations Density 0.047%

    No Known Activations