© 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. 128173
    Prev
    Next
    INDEX
    Explanations

    phrases related to data usage and privacy 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
    illez
    -0.08
    clado
    -0.07
    лан
    -0.07
    ληÏĤ
    -0.07
     linh
    -0.07
    .cum
    -0.07
    ochond
    -0.07
    rowsable
    -0.06
    ajar
    -0.06
    Verb
    -0.06
    POSITIVE LOGITS
    aho
    0.06
    eral
    0.06
    rary
    0.06
    ol
    0.05
    ror
    0.05
    obox
    0.05
     durable
    0.05
     Wave
    0.05
     exceptional
    0.05
    ait
    0.05
    Activations Density 0.000%

    No Known Activations