© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 99020
    Prev
    Next
    INDEX
    Explanations

    the presence of specific contextually significant terms related to conditions or states

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    oyer
    -0.06
    endet
    -0.06
    #af
    -0.06
    raman
    -0.06
    каÑģ
    -0.06
    برد
    -0.06
     Gazette
    -0.06
    leness
    -0.06
    ANTA
    -0.06
    asse
    -0.06
    POSITIVE LOGITS
    ickerView
    0.07
    /lic
    0.07
    iÄĩ
    0.06
    çį
    0.06
     tém
    0.06
    νÏİ
    0.06
    kowski
    0.06
    ay
    0.06
    ricks
    0.06
    Ã¼ÅŁ
    0.06
    Activations Density 0.000%

    No Known Activations