© 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. 30190
    Prev
    Next
    INDEX
    Explanations

    references to small, isolated structures or shelters in a natural setting

    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
     citizenship
    -0.06
     stad
    -0.06
     hills
    -0.06
     parted
    -0.05
    wer
    -0.05
     Lak
    -0.05
    t
    -0.05
     vibr
    -0.05
     curved
    -0.05
     chilled
    -0.05
    POSITIVE LOGITS
    ackle
    0.08
    леÑĤ
    0.08
    ibile
    0.08
    Ïĥον
    0.08
     ValueEventListener
    0.07
    Logs
    0.07
    ingleton
    0.07
    pole
    0.07
    yleft
    0.07
    į°ìĿ´
    0.07
    Activations Density 0.013%

    No Known Activations