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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 104106
    Prev
    Next
    INDEX
    Explanations

    terms related to geological and observational data regarding volcanoes and earthquakes

    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
    opak
    -0.08
    unker
    -0.07
    egin
    -0.06
    ovit
    -0.06
    engin
    -0.06
    :invoke
    -0.06
    anus
    -0.06
    antan
    -0.06
     دÙģاع
    -0.06
    ango
    -0.06
    POSITIVE LOGITS
    (#)
    0.07
     reported
    0.06
    üst
    0.06
    erton
    0.06
     advis
    0.06
    اشت
    0.06
    -dismiss
    0.06
    æĬ¥åijĬ
    0.06
     Amateur
    0.06
     unw
    0.06
    Activations Density 0.001%

    No Known Activations