© 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 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. 85882
    Prev
    Next
    INDEX
    Explanations

    mentions of formal classifications and structured documentation within military contexts

    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
    enus
    -0.07
    ingo
    -0.06
     Garr
    -0.05
    ISTR
    -0.05
    atif
    -0.05
    as
    -0.05
    \
    -0.05
    que
    -0.05
     then
    -0.05
    asia
    -0.05
    POSITIVE LOGITS
    achu
    0.08
    hdl
    0.07
    ousel
    0.07
    serde
    0.07
    olen
    0.07
    onu
    0.07
    normalized
    0.07
    áºł
    0.07
    andle
    0.07
    oru
    0.07
    Activations Density 0.001%

    No Known Activations