© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 94304
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic calls for papers and proposals

    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
    iten
    -0.06
     sophistic
    -0.06
    zzo
    -0.06
    we
    -0.06
    ika
    -0.06
     matters
    -0.06
    zie
    -0.05
    /we
    -0.05
     amen
    -0.05
    ket
    -0.05
    POSITIVE LOGITS
    ibern
    0.07
    оÑĢоз
    0.07
    ditor
    0.07
    ÑĭÑĪ
    0.07
    .cgi
    0.07
     nominations
    0.07
    imat
    0.07
    ÄĽÅ¾
    0.07
    ãĥ¼ãĥĭ
    0.06
    ÏĩεδÏĮν
    0.06
    Activations Density 0.003%

    No Known Activations