© 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. 17544
    Prev
    Next
    INDEX
    Explanations

    various forms of organization, initiatives, and recognitions related to support systems and community resources

    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
    arella
    -0.06
    -0.06
     m
    -0.06
    iew
    -0.06
    adem
    -0.06
    engu
    -0.05
    ullan
    -0.05
     anchor
    -0.05
    itsu
    -0.05
    aign
    -0.05
    POSITIVE LOGITS
     dedicated
    0.19
     devoted
    0.18
     Dedicated
    0.14
     dedicate
    0.14
    ded
    0.13
     dedic
    0.13
    ä¸ĵ
    0.12
     dedi
    0.10
     ä¸ĵ
    0.10
    خصص
    0.10
    Activations Density 0.083%

    No Known Activations