© 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. 62389
    Prev
    Next
    INDEX
    Explanations

    words related to loss or degradation

    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
    niest
    -0.08
    ouro
    -0.08
    enco
    -0.07
    leÅŁik
    -0.07
    ropol
    -0.07
    BJECT
    -0.07
    inç
    -0.07
    rál
    -0.07
    uckles
    -0.07
    sworth
    -0.07
    POSITIVE LOGITS
     handy
    0.07
    ck
    0.06
     hence
    0.05
    AGO
    0.05
     Caldwell
    0.05
     Gos
    0.05
     tot
    0.05
    war
    0.05
     bel
    0.05
     ambit
    0.05
    Activations Density 0.000%

    No Known Activations