© 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. 84266
    Prev
    Next
    INDEX
    Explanations

    terms related to restructuring processes

    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
    uraa
    -0.07
    lesh
    -0.07
    getter
    -0.07
    cura
    -0.07
    inki
    -0.07
    kola
    -0.07
    rijk
    -0.07
    esel
    -0.07
    calar
    -0.07
    ollen
    -0.07
    POSITIVE LOGITS
    acom
    0.07
    ductive
    0.07
    atted
    0.07
    tt
    0.07
    ing
    0.06
    ties
    0.06
    tings
    0.06
    aped
    0.06
    lops
    0.06
    icontrol
    0.06
    Activations Density 0.008%

    No Known Activations