© 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. 127885
    Prev
    Next
    INDEX
    Explanations

    terms related to drowning and water-related incidents

    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
    oint
    -0.08
    iola
    -0.07
    ople
    -0.07
    uite
    -0.06
    ial
    -0.06
    alendar
    -0.06
    loyd
    -0.06
    utable
    -0.06
    chal
    -0.06
    ty
    -0.06
    POSITIVE LOGITS
    hound
    0.08
    æº
    0.08
    edin
    0.08
    ingly
    0.07
    icz
    0.07
    è¾°
    0.07
    -pill
    0.07
    çĢ¬
    0.07
    avigator
    0.06
    hole
    0.06
    Activations Density 0.003%

    No Known Activations