© 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. 84861
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to financial schemes

    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
    sled
    -0.08
    ÑĤаж
    -0.08
    ｡
    -0.07
    ewe
    -0.07
    /her
    -0.07
    ţ
    -0.07
    .si
    -0.07
    Äł
    -0.07
    ̣
    -0.07
    баÑģ
    -0.07
    POSITIVE LOGITS
    ISCO
    0.07
    aeda
    0.07
    ictor
    0.06
    ipeg
    0.06
    STITUTE
    0.06
    ooks
    0.06
    ioxide
    0.06
    atics
    0.06
    occo
    0.06
    ıa
    0.06
    Activations Density 0.033%

    No Known Activations