© 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. 9-LLAMASCOPE-RES-131K
    11. 97688
    Prev
    Next
    INDEX
    Explanations

    references to structural damage and collapse

    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
    гал
    -0.07
     Ø®ÙĦÙĤ
    -0.07
    borg
    -0.07
    одо
    -0.07
    ovenant
    -0.07
    axis
    -0.07
     SIGNAL
    -0.06
    å¿ĺ
    -0.06
    Signal
    -0.06
    tons
    -0.06
    POSITIVE LOGITS
     Western
    0.07
    getRoot
    0.06
     dam
    0.06
    ucci
    0.06
    uto
    0.06
    -collapse
    0.06
     recl
    0.06
     elo
    0.06
     bu
    0.06
    isha
    0.06
    Activations Density 0.012%

    No Known Activations