© 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. 9-LLAMASCOPE-RES-131K
    11. 97716
    Prev
    Next
    INDEX
    Explanations

    concepts related to traceability and accountability

    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
    _RENDERER
    -0.07
    ë¥
    -0.07
    èĩ
    -0.07
    åĬĽçļĦ
    -0.07
    UNCT
    -0.06
    лÑĥги
    -0.06
    å¹¹
    -0.06
    лов
    -0.06
     obed
    -0.06
    .memo
    -0.06
    POSITIVE LOGITS
    zend
    0.07
    orian
    0.06
    ourke
    0.06
    ãĥ³ãĥ
    0.06
    adas
    0.06
    (optional
    0.06
    ala
    0.06
    opi
    0.06
    forder
    0.06
    avanaugh
    0.05
    Activations Density 0.011%

    No Known Activations