© 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 EvalsExportsAPI 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. 126609
    Prev
    Next
    INDEX
    Explanations

    terms related to migration, environmental concerns, and energy policies

    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
    agem
    -0.07
    ÑĢеб
    -0.07
    Chunks
    -0.07
    queued
    -0.07
    mant
    -0.07
    æ¬ł
    -0.06
    ضÛĮ
    -0.06
    irmed
    -0.06
    ضÙĬ
    -0.06
    iset
    -0.06
    POSITIVE LOGITS
     behalf
    0.08
    /github
    0.07
     matters
    0.07
    /topics
    0.07
    -related
    0.07
     Matters
    0.07
    .pdf
    0.07
    ekyll
    0.06
    ous
    0.06
    akespeare
    0.06
    Activations Density 0.030%

    No Known Activations