© 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. 104611
    Prev
    Next
    INDEX
    Explanations

    references to best practices and methodologies

    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
     âĸ³
    -0.08
    imu
    -0.08
    AREST
    -0.07
    ersiz
    -0.07
    ãģªãģŁ
    -0.07
    _tF
    -0.07
    #__
    -0.06
    Ïģαβ
    -0.06
    âijł
    -0.06
    zione
    -0.06
    POSITIVE LOGITS
    ospace
    0.06
     overall
    0.06
     COVID
    0.06
    quate
    0.06
     reck
    0.06
    éĴĪ
    0.06
    bv
    0.06
    nod
    0.06
    966
    0.05
    atak
    0.05
    Activations Density 0.000%

    No Known Activations