© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95277
    Prev
    Next
    INDEX
    Explanations

    terms related to quartz and fishing

    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
    readcr
    -0.07
    Envelope
    -0.07
    ymm
    -0.06
    jamin
    -0.06
    hti
    -0.06
    anke
    -0.06
    zÃŃ
    -0.06
    erb
    -0.06
    ght
    -0.06
    gings
    -0.06
    POSITIVE LOGITS
    ska
    0.09
    ucket
    0.07
    ullo
    0.07
    баÑĩ
    0.07
     Mits
    0.07
    -router
    0.07
    akedirs
    0.07
    µľ
    0.07
    s
    0.07
    ine
    0.07
    Activations Density 0.003%

    No Known Activations