© 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. 81841
    Prev
    Next
    INDEX
    Explanations

    references to political parties and their dynamics

    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
    undler
    -0.07
    hell
    -0.07
    ÑĤÑĮ
    -0.07
    anny
    -0.07
    udas
    -0.07
     jint
    -0.07
    amente
    -0.07
     оÑģÑĮ
    -0.06
     воÑĤ
    -0.06
    ndo
    -0.06
    POSITIVE LOGITS
     simply
    0.09
     actually
    0.07
     is
    0.07
    iz
    0.06
     claim
    0.06
     because
    0.06
     or
    0.06
     Commod
    0.06
     merely
    0.06
     etc
    0.06
    Activations Density 0.025%

    No Known Activations