© 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 EvalsExportsAPI 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. 106628
    Prev
    Next
    INDEX
    Explanations

    expressions related to family or pets

    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
    759
    -0.06
    799
    -0.06
     Yah
    -0.06
     Cunningham
    -0.06
    524
    -0.06
    лек
    -0.06
    svn
    -0.06
    isku
    -0.06
    à¤Ĥ
    -0.06
    Binding
    -0.05
    POSITIVE LOGITS
     fur
    0.07
     paw
    0.07
    esz
    0.06
    builtin
    0.06
    arf
    0.06
    fur
    0.06
    omp
    0.06
     -------------------------------------------------------------------------
    0.06
    ande
    0.06
    woff
    0.06
    Activations Density 0.006%

    No Known Activations