© 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 EvalsExportsinterp-engineNEWAPI 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. 120996
    Prev
    Next
    INDEX
    Explanations

    references to nuclear weapons and military strategies

    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
     filtr
    -0.06
     Orta
    -0.06
     Mandal
    -0.06
    affen
    -0.06
    ands
    -0.06
    andle
    -0.06
     PageInfo
    -0.06
     ÑĢÑĥк
    -0.06
    imet
    -0.06
    ãĥ³ãĥĦ
    -0.05
    POSITIVE LOGITS
     nuclear
    0.10
     Nuclear
    0.09
    ersh
    0.08
    hlas
    0.08
    uclear
    0.08
     plut
    0.08
    #__
    0.07
    emouth
    0.07
    ingles
    0.07
    Fault
    0.07
    Activations Density 0.007%

    No Known Activations