© 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. 15-LLAMASCOPE-RES-131K
    11. 61346
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to liability and actions

    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
    uggle
    -0.07
    &R
    -0.06
    деÑĤ
    -0.06
    isia
    -0.06
    øy
    -0.06
    igos
    -0.06
    creativecommons
    -0.06
    czy
    -0.06
    acher
    -0.06
    iert
    -0.06
    POSITIVE LOGITS
    arith
    0.07
    Streamer
    0.07
    rie
    0.07
    axon
    0.07
    _blocking
    0.07
    برÛĮ
    0.06
    ecer
    0.06
    ioni
    0.06
    SPAN
    0.06
    αιο
    0.06
    Activations Density 0.000%

    No Known Activations