© 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 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. 61007
    Prev
    Next
    INDEX
    Explanations

    terms related to identity and archaeology

    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
    raman
    -0.07
    (enabled
    -0.06
     demokrat
    -0.06
    chner
    -0.06
     port
    -0.06
    vell
    -0.06
     Atmos
    -0.06
    addColumn
    -0.06
     lif
    -0.06
     Libertarian
    -0.06
    POSITIVE LOGITS
     geo
    0.07
    ellite
    0.07
    LayoutManager
    0.07
    geo
    0.07
    éļĨ
    0.06
    onical
    0.06
    ahn
    0.06
     partitions
    0.06
     Partition
    0.06
     Dien
    0.06
    Activations Density 0.001%

    No Known Activations