© 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. 62058
    Prev
    Next
    INDEX
    Explanations

    numerical values or references to financial worth

    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
     Nel
    -0.06
    ivy
    -0.06
    wt
    -0.06
    ocos
    -0.06
    -unit
    -0.06
     units
    -0.06
    ConverterFactory
    -0.05
    iving
    -0.05
    éal
    -0.05
    agoon
    -0.05
    POSITIVE LOGITS
     GPLv
    0.07
    oon
    0.07
    ennen
    0.07
    jÃŃt
    0.06
    emain
    0.06
    .unlock
    0.06
    ickerView
    0.06
     '../../../../../
    0.06
    ORITY
    0.06
    galement
    0.06
    Activations Density 0.002%

    No Known Activations