© 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. 4155
    Prev
    Next
    INDEX
    Explanations

    references to additional reading or related stories

    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
    lý
    -0.08
    witter
    -0.07
    isman
    -0.07
    owie
    -0.07
    ellar
    -0.06
    @student
    -0.06
    lÃŃ
    -0.06
    ienne
    -0.06
    _TestCase
    -0.06
    orrent
    -0.06
    POSITIVE LOGITS
    usch
    0.06
    аÑĤи
    0.06
     Mare
    0.06
    bett
    0.06
    opoulos
    0.06
    rub
    0.06
     rub
    0.06
    thus
    0.05
    totals
    0.05
     Polar
    0.05
    Activations Density 0.012%

    No Known Activations