© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96319
    Prev
    Next
    INDEX
    Explanations

    references to swimwear or beach attire

    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
    .scalablytyped
    -0.09
    onis
    -0.07
    luet
    -0.07
    heimer
    -0.07
    shit
    -0.06
    OwnProperty
    -0.06
    sizei
    -0.06
    acons
    -0.06
    /generated
    -0.06
    OffsetTable
    -0.06
    POSITIVE LOGITS
    rove
    0.06
    utto
    0.06
    ream
    0.06
    εÏį
    0.06
    loat
    0.06
    808
    0.06
    reon
    0.06
    acked
    0.06
    707
    0.06
    ¸
    0.06
    Activations Density 0.003%

    No Known Activations