© 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. 27935
    Prev
    Next
    INDEX
    Explanations

    references to collaboration and organization 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
     dynam
    -0.06
    iled
    -0.06
    e
    -0.06
    enaire
    -0.06
     diabetic
    -0.06
     wat
    -0.05
     waterproof
    -0.05
    ,
    -0.05
    _wire
    -0.05
    ROC
    -0.05
    POSITIVE LOGITS
    æĵ¦
    0.07
    otor
    0.07
    Bars
    0.07
     ragaz
    0.07
    acher
    0.07
    SYS
    0.07
    ιÏĥ
    0.06
    íĺ
    0.06
    edio
    0.06
    ινÏĮ
    0.06
    Activations Density 0.049%

    No Known Activations