© 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. 95220
    Prev
    Next
    INDEX
    Explanations

    references to groups or teams, particularly using the term "squad" in various 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
    uve
    -0.09
    place
    -0.08
    ROAD
    -0.07
    ноÑģÑı
    -0.07
    chl
    -0.07
    askan
    -0.07
    -place
    -0.07
    creasing
    -0.07
    places
    -0.07
    essian
    -0.07
    POSITIVE LOGITS
    ä¼į
    0.11
    rons
    0.09
    member
    0.09
    ra
    0.07
    wagon
    0.07
    oman
    0.07
    rio
    0.07
    axon
    0.07
     member
    0.07
     members
    0.07
    Activations Density 0.008%

    No Known Activations