© 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. 17-LLAMASCOPE-RES-131K
    11. 5128
    Prev
    Next
    INDEX
    Explanations

    terms related to decay or deterioration

    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
    ustin
    -0.06
     Downs
    -0.06
    ses
    -0.06
    tro
    -0.06
     Morr
    -0.06
    shot
    -0.06
    zin
    -0.06
    tractive
    -0.05
    tool
    -0.05
    æĿŁ
    -0.05
    POSITIVE LOGITS
    obuf
    0.09
    egg
    0.09
    &o
    0.08
     Decay
    0.07
    omics
    0.07
    /null
    0.07
    mdb
    0.07
    ness
    0.07
    anske
    0.07
     hết
    0.07
    Activations Density 0.002%

    No Known Activations