© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 4082
    Prev
    Next
    INDEX
    Explanations

    references to military bases and related military terminology

    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
    ship
    -0.10
    ships
    -0.10
    rei
    -0.08
    self
    -0.08
    sdale
    -0.07
    lied
    -0.07
    shift
    -0.07
    reich
    -0.07
     viên
    -0.07
    sh
    -0.07
    POSITIVE LOGITS
    camp
    0.10
    plate
    0.09
    gfx
    0.08
    band
    0.08
    gger
    0.08
    /base
    0.07
    elor
    0.07
    coat
    0.07
    casting
    0.07
     hạ
    0.07
    Activations Density 0.062%

    No Known Activations