© 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. 86411
    Prev
    Next
    INDEX
    Explanations

    words related to societal struggles and efforts for improvement

    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
    onta
    -0.07
    ÙĬØ«
    -0.07
    kv
    -0.07
    ãĥ³ãĤ¿
    -0.07
     Weston
    -0.06
    kit
    -0.06
     огÑĢа
    -0.06
    ãĤ¼
    -0.06
    getApplication
    -0.06
    .pad
    -0.06
    POSITIVE LOGITS
     regarding
    0.07
    对äºİ
    0.07
     against
    0.07
     towards
    0.07
     for
    0.06
    atif
    0.06
     toward
    0.06
    contri
    0.06
     regards
    0.06
    odiac
    0.06
    Activations Density 0.059%

    No Known Activations