© 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. 94779
    Prev
    Next
    INDEX
    Explanations

    references to actions required for social and economic development

    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
    Ỽ
    -0.09
    .tm
    -0.09
    Ñģклад
    -0.08
    ãģĭãģij
    -0.08
    AMESPACE
    -0.08
    ForResource
    -0.08
     инÑĦоÑĢма
    -0.08
    SSERT
    -0.08
     Baghd
    -0.07
     iddi
    -0.07
    POSITIVE LOGITS
     whether
    0.07
    ighton
    0.06
     and
    0.06
     upper
    0.06
    opi
    0.06
    ,
    0.06
    613
    0.06
     (
    0.06
    /
    0.05
     fe
    0.05
    Activations Density 0.038%

    No Known Activations