© 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. 15-LLAMASCOPE-RES-131K
    11. 86472
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to immigration policies and their social implications

    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
     Ars
    -0.07
    ru
    -0.07
    Kid
    -0.06
    igo
    -0.06
    ropp
    -0.06
    oted
    -0.06
    rid
    -0.06
    brid
    -0.06
    unn
    -0.06
     Kid
    -0.06
    POSITIVE LOGITS
    eka
    0.07
    ajo
    0.07
     foot
    0.06
    Sharper
    0.06
    xes
    0.06
    0.06
     paras
    0.06
    aad
    0.06
     crypt
    0.06
    ekler
    0.06
    Activations Density 0.025%

    No Known Activations