© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 106211
    Prev
    Next
    INDEX
    Explanations

    terms related to "otherness" or the concept of the "Other."

    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
    koli
    -0.08
    rat
    -0.07
    adera
    -0.07
    uras
    -0.07
     others
    -0.07
    adesh
    -0.07
    vale
    -0.07
    taire
    -0.07
    ptive
    -0.07
    ulk
    -0.06
    POSITIVE LOGITS
    ness
    0.07
    ÙĪÛĮÙĩ
    0.07
    mes
    0.07
    iginal
    0.06
    rea
    0.06
    langs
    0.06
    world
    0.06
    -than
    0.06
    apeutic
    0.06
    NESS
    0.06
    Activations Density 0.017%

    No Known Activations