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

    Neuronpedia

    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. 28551
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptions associated with military vehicles and equipment

    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
    usz
    -0.07
    ablish
    -0.06
     rop
    -0.06
    iversity
    -0.06
     boats
    -0.06
     Dan
    -0.06
    ener
    -0.06
     Fallen
    -0.06
     bou
    -0.06
    edium
    -0.06
    POSITIVE LOGITS
    URRE
    0.07
     configuration
    0.07
    .rar
    0.07
    ibal
    0.07
    Seats
    0.07
    urr
    0.06
     capabilities
    0.06
    configuration
    0.06
     capability
    0.06
    OnInit
    0.06
    Activations Density 0.056%

    No Known Activations