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. 22-LLAMASCOPE-RES-131K
    6. 4395
    Prev
    Next
    INDEX
    Explanations

    references to historical disasters or significant events related to nuclear issues

    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
     dew
    -0.06
    .xyz
    -0.06
    ruz
    -0.06
    fmt
    -0.05
    icide
    -0.05
    _Meta
    -0.05
    ottes
    -0.05
    åĿĽ
    -0.05
    æĽ°
    -0.05
    xac
    -0.05
    POSITIVE LOGITS
     Chern
    0.08
    esium
    0.08
     radiation
    0.08
     nuclear
    0.08
     Maiden
    0.07
     disaster
    0.07
     meltdown
    0.07
    ovky
    0.07
     Radiation
    0.07
    tsy
    0.07
    Activations Density 0.000%

    No Known Activations