© 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. 18309
    Prev
    Next
    INDEX
    Explanations

    terms related to multidisciplinarity and antimicrobial properties

    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
    adero
    -0.07
    aphore
    -0.07
    Å¡et
    -0.07
    jeme
    -0.07
    -widgets
    -0.07
    edom
    -0.06
    zman
    -0.06
    icerca
    -0.06
    ipherals
    -0.06
    ÑĪÑĥ
    -0.06
    POSITIVE LOGITS
    most
    0.08
    ry
    0.08
    ly
    0.07
    ust
    0.07
    rist
    0.07
    led
    0.07
    la
    0.07
    na
    0.07
    p
    0.07
    ub
    0.07
    Activations Density 0.022%

    No Known Activations