© 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. 17-LLAMASCOPE-RES-131K
    11. 126743
    Prev
    Next
    INDEX
    Explanations

    terms related to volcanic activity

    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
    iral
    -0.06
    ornado
    -0.06
    META
    -0.06
    ÏĨη
    -0.06
    ateria
    -0.06
    身
    -0.06
    _bn
    -0.05
     Beverage
    -0.05
    ilim
    -0.05
    丸
    -0.05
    POSITIVE LOGITS
     eruption
    0.08
     lava
    0.08
     erupted
    0.07
     magma
    0.07
     erupt
    0.07
     nue
    0.07
     volcano
    0.07
     вÑĥл
    0.07
     ash
    0.07
     volcan
    0.07
    Activations Density 0.008%

    No Known Activations