© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87459
    Prev
    Next
    INDEX
    Explanations

    words related to the decoration or embellishment of objects or environments

    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
    andra
    -0.07
    irsch
    -0.07
    oriasis
    -0.07
    دÙĨ
    -0.06
    ãĥĨãĥ«
    -0.06
    ër
    -0.06
     PROGMEM
    -0.06
    oder
    -0.06
    berman
    -0.06
    ioni
    -0.06
    POSITIVE LOGITS
     with
    0.12
     withd
    0.07
    andler
    0.07
    lán
    0.07
     by
    0.06
    umber
    0.06
    ý
    0.06
    with
    0.06
     dengan
    0.06
    меÑĩ
    0.06
    Activations Density 0.033%

    No Known Activations