© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17-LLAMASCOPE-RES-131K
    11. 78858
    Prev
    Next
    INDEX
    Explanations

    elements related to documentation and credentials

    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
     current
    -0.06
    ucher
    -0.06
     approx
    -0.06
     CT
    -0.06
     as
    -0.05
     new
    -0.05
    orama
    -0.05
    CT
    -0.05
    r
    -0.05
     Witt
    -0.05
    POSITIVE LOGITS
     pes
    0.08
    assin
    0.07
    InstanceOf
    0.07
    821
    0.07
    pes
    0.07
    mentioned
    0.07
    VertexBuffer
    0.07
    ibernate
    0.07
    ë¡ľëĤĺ
    0.07
    ÑĢоÑģÑĤо
    0.07
    Activations Density 0.066%

    No Known Activations