© 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. 126512
    Prev
    Next
    INDEX
    Explanations

    iterations of 'd' in various contexts

    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
    .nih
    -0.08
    177
    -0.07
    bek
    -0.07
     Kı
    -0.07
    olls
    -0.07
    ä¸ĺ
    -0.07
    iceps
    -0.06
    ogr
    -0.06
    ób
    -0.06
    rv
    -0.06
    POSITIVE LOGITS
    usi
    0.07
    iani
    0.06
    oren
    0.06
    ron
    0.06
     dol
    0.06
     fl
    0.06
     d
    0.06
    yr
    0.06
    ÑıÑĩ
    0.06
     Pop
    0.06
    Activations Density 0.012%

    No Known Activations