© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 88047
    Prev
    Next
    INDEX
    Explanations

    special characters or unique alphabets within the text

    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
    айд
    -0.07
    /rfc
    -0.07
    ÃŃcia
    -0.07
    nock
    -0.07
    aidu
    -0.07
    .sam
    -0.06
    ppo
    -0.06
     den
    -0.06
    anke
    -0.06
    Eigen
    -0.06
    POSITIVE LOGITS
    طاÙĦ
    0.06
     Permission
    0.06
    éĿ
    0.06
    iveau
    0.06
    Permission
    0.06
     Tit
    0.06
     embod
    0.06
    amba
    0.06
    ela
    0.06
    (fabs
    0.06
    Activations Density 0.001%

    No Known Activations