© 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. 119779
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    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
    iedo
    -0.07
    uff
    -0.06
    wart
    -0.06
    geries
    -0.06
     peri
    -0.06
    UFF
    -0.06
    162
    -0.05
    endet
    -0.05
     cf
    -0.05
    -links
    -0.05
    POSITIVE LOGITS
    rych
    0.08
    ruk
    0.07
    .wik
    0.07
    dál
    0.07
    lie
    0.07
    ocha
    0.07
     acomp
    0.06
    Ú¯ÙĪÛĮ
    0.06
    ÑģÑĤвенное
    0.06
    issance
    0.06
    Activations Density 0.001%

    No Known Activations