© 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. 39278
    Prev
    Next
    INDEX
    Explanations

    keywords related to the condition and quality of books or materials

    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
    ooter
    -0.07
    ÑĢÑĥз
    -0.06
    riers
    -0.06
    asper
    -0.06
    _vlog
    -0.06
    idle
    -0.06
    ROWS
    -0.05
    Interrupt
    -0.05
     mog
    -0.05
    .scalablytyped
    -0.05
    POSITIVE LOGITS
    oba
    0.08
    yal
    0.08
    edo
    0.07
    наÑħ
    0.07
    ouble
    0.07
    omat
    0.07
    æľ
    0.07
     protective
    0.07
     Protective
    0.06
     dál
    0.06
    Activations Density 0.003%

    No Known Activations