© 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. 3651
    Prev
    Next
    INDEX
    Explanations

    key phrases related to corporate leadership and innovation in technology and communications

    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
    orte
    -0.06
    iser
    -0.06
     spec
    -0.06
    usan
    -0.06
    orthy
    -0.05
    UNS
    -0.05
     —
    -0.05
    tern
    -0.05
     resp
    -0.05
    uns
    -0.05
    POSITIVE LOGITS
    ħn
    0.07
     meiden
    0.07
    riba
    0.07
    สำà¹Ģร
    0.07
    kos
    0.07
    ãĤµãĤ¤
    0.07
    RunWith
    0.06
    dü
    0.06
    _formats
    0.06
    ابÙĦ
    0.06
    Activations Density 0.015%

    No Known Activations