© 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. 18493
    Prev
    Next
    INDEX
    Explanations

    specific years or date references within the document

    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
    EFR
    -0.07
    hausen
    -0.06
    arend
    -0.06
    148
    -0.06
    burgh
    -0.06
    letter
    -0.06
    arbeit
    -0.06
    obe
    -0.06
     mere
    -0.06
     nation
    -0.06
    POSITIVE LOGITS
    LOAT
    0.07
    ạc
    0.07
    ë²Į
    0.07
    ç½²
    0.07
    ONA
    0.07
    OKIE
    0.07
    unci
    0.07
     éĻ
    0.07
    èµĸ
    0.07
    inous
    0.06
    Activations Density 0.021%

    No Known Activations