© 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. 73182
    Prev
    Next
    INDEX
    Explanations

    references to Java programming and related libraries

    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
    ëľ
    -0.08
    alach
    -0.08
    ¢åįķ
    -0.07
    .liferay
    -0.07
    ubbo
    -0.07
    arov
    -0.07
    opr
    -0.07
    culus
    -0.07
    cura
    -0.07
    oad
    -0.06
    POSITIVE LOGITS
    mailer
    0.07
    reich
    0.06
    aml
    0.06
     Spi
    0.06
    ë§ĮìĽIJ
    0.06
    ulan
    0.06
    æĤī
    0.06
    ObjectId
    0.05
     desar
    0.05
    á»įn
    0.05
    Activations Density 0.000%

    No Known Activations