© 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. 41565
    Prev
    Next
    INDEX
    Explanations

    expressions of remembrance and tribute in the context of significant events

    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
    sonian
    -0.08
    à¹Ģà¸ļ
    -0.07
    ÑħÑĥ
    -0.07
    ,retain
    -0.07
    WISE
    -0.07
    POCH
    -0.07
    .nih
    -0.06
    çľī
    -0.06
    argas
    -0.06
    tain
    -0.06
    POSITIVE LOGITS
     trib
    0.09
    tributes
    0.08
     dedic
    0.07
     grieving
    0.06
    apper
    0.06
     tribute
    0.06
     mourning
    0.06
     devastated
    0.06
     dedicated
    0.06
     loss
    0.06
    Activations Density 0.005%

    No Known Activations