© 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. 41423
    Prev
    Next
    INDEX
    Explanations

    monetary values and references to fine materials or craftsmanship

    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
    896
    -0.07
    etur
    -0.07
    ç«ł
    -0.06
     gratuites
    -0.06
    peare
    -0.06
     Actor
    -0.06
    readcr
    -0.06
    mpar
    -0.06
    reuse
    -0.06
    renom
    -0.06
    POSITIVE LOGITS
    Ñĥмов
    0.07
    _descr
    0.07
    mai
    0.06
    ummings
    0.06
    iple
    0.06
    imal
    0.06
     Obr
    0.06
     Intr
    0.06
     undocumented
    0.06
     collectors
    0.05
    Activations Density 0.000%

    No Known Activations