© 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. 28045
    Prev
    Next
    INDEX
    Explanations

    phrases related to restarting or beginning anew

    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
    hev
    -0.08
     Permanent
    -0.06
    áºŃu
    -0.06
    Permanent
    -0.06
    chner
    -0.06
    fel
    -0.06
    ushing
    -0.06
    ÑıÑĤи
    -0.06
    ums
    -0.06
     continued
    -0.06
    POSITIVE LOGITS
     again
    0.15
     Again
    0.13
    again
    0.13
    Again
    0.11
     novamente
    0.11
     wieder
    0.11
    _again
    0.10
     AGAIN
    0.10
    AGAIN
    0.10
    éĩįæĸ°
    0.10
    Activations Density 0.031%

    No Known Activations