© 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. 57320
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting symbols

    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
     Abed
    -0.07
    724
    -0.06
    )./
    -0.06
     hare
    -0.06
    naz
    -0.06
     Kimber
    -0.06
    icias
    -0.06
    ervas
    -0.06
     //@
    -0.06
    Calibri
    -0.06
    POSITIVE LOGITS
    omp
    0.07
    ÙĪÙĬ
    0.07
    OTE
    0.07
    olo
    0.07
     gee
    0.07
    Å¡tÄĽnÃŃ
    0.06
    물
    0.06
    ACKET
    0.06
    kowski
    0.06
    zers
    0.06
    Activations Density 0.004%

    No Known Activations