Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16497
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to natural disasters and their impacts

    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
    xon
    -0.07
    .hl
    -0.07
    št
    -0.07
    ÙĥÙĬ
    -0.06
     Ùħخت
    -0.06
    _recent
    -0.06
    nero
    -0.06
    canf
    -0.06
     INCIDENT
    -0.06
    icina
    -0.06
    POSITIVE LOGITS
    ehr
    0.07
     estimated
    0.06
    amac
    0.06
     social
    0.06
    Lua
    0.06
     Hoover
    0.06
    ISA
    0.06
     Elephant
    0.06
    isa
    0.06
     leve
    0.06
    Activations Density 0.008%

    No Known Activations