© 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. 78453
    Prev
    Next
    INDEX
    Explanations

    references to frequency and duration of activities

    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
    eyle
    -0.08
    aģı
    -0.08
    دارÛĮ
    -0.07
     ÑģÑħод
    -0.07
    esome
    -0.07
    ATAL
    -0.07
    ainter
    -0.07
    crate
    -0.07
    'o
    -0.07
    incr
    -0.07
    POSITIVE LOGITS
    /month
    0.07
     minimum
    0.06
    ettle
    0.06
     devoted
    0.06
    lay
    0.06
    ãģĨãģ¡
    0.05
     Haz
    0.05
    fy
    0.05
     Wyn
    0.05
     Eudicots
    0.05
    Activations Density 0.009%

    No Known Activations