© 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. 119340
    Prev
    Next
    INDEX
    Explanations

    words related to qualifications or descriptors

    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
    ensing
    -0.07
    Ŀ
    -0.06
    uraa
    -0.06
    inka
    -0.06
    ekil
    -0.06
    arme
    -0.06
    omba
    -0.06
    ipeg
    -0.06
    åĢ
    -0.06
    º
    -0.06
    POSITIVE LOGITS
    cion
    0.07
    हर
    0.07
    EDIA
    0.06
     knull
    0.06
    redits
    0.06
    iser
    0.06
    lick
    0.06
     wel
    0.06
    Wnd
    0.06
    جÙĬ
    0.06
    Activations Density 0.067%

    No Known Activations