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

    Neuronpedia

    Jacobian LensNEW
    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. 29461
    Prev
    Next
    INDEX
    Explanations

    instances of physical destruction or damage in disaster contexts

    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
    окÑģи
    -0.08
    zim
    -0.07
    ãĥªãĥ³ãĤ°
    -0.07
     semanas
    -0.07
    _REUSE
    -0.07
     actionTypes
    -0.07
    浩
    -0.07
    ulton
    -0.07
    reo
    -0.07
    æĴŃ
    -0.07
    POSITIVE LOGITS
    uga
    0.08
     reports
    0.07
     light
    0.06
    103
    0.06
     everywhere
    0.06
    0.06
    itur
    0.06
     reported
    0.06
    uvo
    0.06
     elderly
    0.06
    Activations Density 0.006%

    No Known Activations