Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5724
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to object initialization

    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
    oser
    -0.07
    ottage
    -0.06
    ashi
    -0.06
    _ED
    -0.06
    WARE
    -0.06
    otas
    -0.06
    sti
    -0.06
    hill
    -0.06
    alf
    -0.06
    arro
    -0.05
    POSITIVE LOGITS
    enler
    0.07
    577
    0.07
    WXYZ
    0.07
    ìļķ
    0.07
    .createObject
    0.07
    yntax
    0.07
     super
    0.06
    patial
    0.06
     vill
    0.06
    ÅĪ
    0.06
    Activations Density 0.002%

    No Known Activations