© 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. 61807
    Prev
    Next
    INDEX
    Explanations

    date and time-related information in a specific format

    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
    ÐļÐŀ
    -0.07
    vant
    -0.07
    ivol
    -0.07
    ppe
    -0.07
    ÑĢÑĥÑĪ
    -0.07
    oyer
    -0.06
    istro
    -0.06
    pii
    -0.06
    olla
    -0.06
    abee
    -0.06
    POSITIVE LOGITS
    дам
    0.07
    _Reference
    0.06
    jer
    0.06
    ิà¹Ī
    0.06
     شع
    0.06
    ügen
    0.06
     Agency
    0.06
     pedig
    0.06
    uct
    0.06
     inher
    0.05
    Activations Density 0.004%

    No Known Activations