© 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. 41873
    Prev
    Next
    INDEX
    Explanations

    references to military actions or entities

    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
    istrovstvÃŃ
    -0.09
    warts
    -0.08
    istry
    -0.07
    hled
    -0.07
    lessly
    -0.07
    heim
    -0.07
    olian
    -0.07
    rij
    -0.07
    ï¸ı
    -0.07
    Ñħод
    -0.07
    POSITIVE LOGITS
    -grade
    0.09
    /nav
    0.07
    /pol
    0.07
     grade
    0.07
    /security
    0.07
    mil
    0.07
    -ind
    0.06
    -commercial
    0.06
     personnel
    0.06
     Eh
    0.06
    Activations Density 0.016%

    No Known Activations