© 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. 81590
    Prev
    Next
    INDEX
    Explanations

    words related to declines or reductions in various contexts

    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
    obi
    -0.07
    rike
    -0.07
    768
    -0.06
    nici
    -0.06
    zsche
    -0.06
    ARGIN
    -0.06
    eniable
    -0.06
    PressEvent
    -0.06
     Else
    -0.06
    ned
    -0.06
    POSITIVE LOGITS
    oning
    0.07
    ément
    0.07
     inv
    0.07
    ara
    0.06
     Cl
    0.06
    ipping
    0.06
     Feinstein
    0.06
    anzeigen
    0.06
     mim
    0.06
    uy
    0.06
    Activations Density 0.022%

    No Known Activations