© 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 EvalsExportsAPI 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. 96653
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions, qualifications, and suitability in a legal or financial context

    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
    istrovstvÃŃ
    -0.08
    arat
    -0.07
    uste
    -0.07
    osaur
    -0.07
     zav
    -0.06
    azor
    -0.06
    irk
    -0.06
     MANUAL
    -0.06
    _ENUM
    -0.06
    amental
    -0.06
    POSITIVE LOGITS
    MBED
    0.06
    ãĤ¹ãĥŀ
    0.06
     finally
    0.06
    _MB
    0.06
    ÑĢиÑģÑĤ
    0.06
    obel
    0.06
    TEE
    0.06
    assi
    0.06
     voc
    0.06
     Åŀubat
    0.05
    Activations Density 0.001%

    No Known Activations