© 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. 72652
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and character sequences commonly found in data formats or code

    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
     Vincent
    -0.06
     Bowman
    -0.06
    .rm
    -0.06
    碼
    -0.06
    cheid
    -0.06
    ç¤
    -0.06
    klä
    -0.06
    èįī
    -0.06
     Bellev
    -0.06
    .btnSave
    -0.06
    POSITIVE LOGITS
     engulf
    0.06
    agnost
    0.06
     Suc
    0.06
    descr
    0.06
     Miz
    0.06
    neau
    0.06
    reta
    0.06
    çĿ
    0.06
    agu
    0.06
    agnet
    0.06
    Activations Density 0.000%

    No Known Activations