© 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. 80948
    Prev
    Next
    INDEX
    Explanations

    details about military ranks and positions

    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
     Airlines
    -0.07
    yen
    -0.07
    ãģĭãĤĭ
    -0.07
    vir
    -0.06
     terrain
    -0.06
     airports
    -0.06
     luggage
    -0.06
     armies
    -0.06
     airlines
    -0.06
     CLIENT
    -0.06
    POSITIVE LOGITS
     underway
    0.09
     vessels
    0.08
     vessel
    0.08
     recom
    0.07
     deck
    0.07
    deck
    0.07
     ship
    0.07
    æĻ
    0.07
     Depth
    0.07
    Depth
    0.07
    Activations Density 0.022%

    No Known Activations