© 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. 97899
    Prev
    Next
    INDEX
    Explanations

    topics related to artistic expression and community engagement, particularly among young and marginalized creatives

    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
    osed
    -0.07
    ouri
    -0.07
    xit
    -0.07
    osit
    -0.06
    onga
    -0.06
    adro
    -0.06
    zel
    -0.06
    157
    -0.06
    oun
    -0.06
    jl
    -0.06
    POSITIVE LOGITS
    гÑĢад
    0.07
    OVÃģ
    0.07
    éĿ©åij½
    0.07
    .mi
    0.07
     coinc
    0.06
    FixedSize
    0.06
    .literal
    0.06
    олн
    0.06
     neighb
    0.06
     talents
    0.06
    Activations Density 0.061%

    No Known Activations