© 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. 17-LLAMASCOPE-RES-131K
    11. 89504
    Prev
    Next
    INDEX
    Explanations

    various types of formatting or punctuation marks

    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
    enas
    -0.07
    ovit
    -0.07
     aup
    -0.07
    à¥Ĥष
    -0.06
    agu
    -0.06
    един
    -0.06
    amu
    -0.06
    loon
    -0.06
    à¥ģष
    -0.06
    enne
    -0.06
    POSITIVE LOGITS
    ureka
    0.07
    æĤł
    0.06
    ephir
    0.06
    obox
    0.06
     cap
    0.06
    аÑĤа
    0.05
    vv
    0.05
    Å¡ak
    0.05
    ruk
    0.05
     Lafayette
    0.05
    Activations Density 0.001%

    No Known Activations