© 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. 15-LLAMASCOPE-RES-131K
    6. 27533
    Prev
    Next
    INDEX
    Explanations

    references to inclusivity and the presence of diverse groups

    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
     treff
    -0.09
    há
    -0.07
    znám
    -0.07
    ÑģÑıг
    -0.07
    cene
    -0.07
    lsi
    -0.07
     Všech
    -0.07
    ÑĢава
    -0.07
    ::.
    -0.07
    roperty
    -0.07
    POSITIVE LOGITS
     across
    0.07
    ornings
    0.07
     different
    0.06
    /to
    0.06
     elsewhere
    0.06
     perspective
    0.06
     walks
    0.06
     around
    0.06
     perspectives
    0.06
     camp
    0.06
    Activations Density 0.008%

    No Known Activations