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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 74828
    Prev
    Next
    INDEX
    Explanations

    references to military defense systems and technologies

    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
    acz
    -0.07
    oteca
    -0.07
     PIXI
    -0.07
    PÅĻÃŃ
    -0.07
    ucha
    -0.07
    ostel
    -0.07
    imensional
    -0.06
    ableObject
    -0.06
     Sesso
    -0.06
    achen
    -0.06
    POSITIVE LOGITS
     Training
    0.06
     pe
    0.06
    Training
    0.06
     training
    0.06
    .pe
    0.06
     var
    0.06
     Hamm
    0.06
     Feder
    0.06
     numer
    0.06
     agencies
    0.06
    Activations Density 0.041%

    No Known Activations