© 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. 42312
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize self-sufficiency and the concept of living off one's own resources or talents

    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
    odon
    -0.07
    emma
    -0.07
    askell
    -0.06
    ãĥĪãĥ«
    -0.06
    ignon
    -0.06
    еÑĢÑĪ
    -0.06
    eature
    -0.06
    mi
    -0.06
    ibel
    -0.06
    otton
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.06
    responseData
    0.06
     thick
    0.06
     thin
    0.06
    ocs
    0.06
     subs
    0.06
     stip
    0.06
    ائرة
    0.06
     campuses
    0.06
     laure
    0.05
    Activations Density 0.013%

    No Known Activations