© 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. 41594
    Prev
    Next
    INDEX
    Explanations

    punctuation and end-of-sentence markers

    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
    Therefore
    -0.07
     Therefore
    -0.07
     daher
    -0.07
     therefore
    -0.06
    окÑĢема
    -0.06
    umpt
    -0.06
    encil
    -0.06
    alah
    -0.06
     ê·¸ëŀĺìĦľ
    -0.06
    aniu
    -0.06
    POSITIVE LOGITS
    iscard
    0.07
     why
    0.07
     although
    0.07
     ÑħоÑĤÑı
    0.07
     preced
    0.07
    ÙĦاÙĤ
    0.07
    Why
    0.07
     Why
    0.06
     rais
    0.06
     bil
    0.06
    Activations Density 0.017%

    No Known Activations