© 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. 85786
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" 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
    RIES
    -0.07
    alim
    -0.07
    riba
    -0.06
    URN
    -0.06
    zug
    -0.06
    ruba
    -0.06
    tera
    -0.06
    itol
    -0.06
    ttp
    -0.06
    iversit
    -0.06
    POSITIVE LOGITS
    .BorderFactory
    0.07
    rogen
    0.06
     Suk
    0.06
    utely
    0.06
    il
    0.06
     Coco
    0.06
     ion
    0.06
     Sok
    0.06
    367
    0.06
     Ion
    0.06
    Activations Density 0.015%

    No Known Activations