© 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. 108464
    Prev
    Next
    INDEX
    Explanations

    keywords related to complex systems and structures

    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
    ullen
    -0.07
    avenport
    -0.07
    (and
    -0.07
    ownt
    -0.07
     tÃŃm
    -0.07
    erro
    -0.07
     metav
    -0.07
     bottoms
    -0.07
    egal
    -0.07
    оба
    -0.07
    POSITIVE LOGITS
     pedig
    0.10
    isque
    0.09
    ãĤĪãģ³
    0.08
     etc
    0.07
     nd
    0.06
     коÑĤоÑĢого
    0.06
    enor
    0.06
    ½
    0.06
     коÑĤоÑĢÑĭÑħ
    0.06
     же
    0.06
    Activations Density 0.222%

    No Known Activations