© 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. 69521
    Prev
    Next
    INDEX
    Explanations

    references to aircraft and their related technical details

    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
     itself
    -0.09
    (s
    -0.09
    (es
    -0.07
     porr
    -0.06
    [s
    -0.06
     Sanat
    -0.06
    posit
    -0.06
    asio
    -0.06
    combe
    -0.06
    ancement
    -0.06
    POSITIVE LOGITS
     themselves
    0.11
    s
    0.08
     thems
    0.08
    folk
    0.07
    Ùĩ
    0.07
    iasi
    0.07
     koje
    0.07
     اÙĦØ°ÙĬÙĨ
    0.07
    们
    0.07
     коÑĤоÑĢÑĭе
    0.07
    Activations Density 0.080%

    No Known Activations