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. MLP Out
    5. 29-LLAMASCOPE-MLP-131K
    6. 5079
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to measurements or quantities

    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
    ZA
    -0.06
    xad
    -0.06
     plane
    -0.06
     age
    -0.06
    rella
    -0.06
    arus
    -0.06
    ãĥĥãĤ«ãĥ¼
    -0.06
    ź
    -0.06
     Marcos
    -0.06
    ieres
    -0.05
    POSITIVE LOGITS
    endregion
    0.07
    bear
    0.07
    ãģļ
    0.07
    charts
    0.07
    ICI
    0.07
    throw
    0.07
     Edmund
    0.06
    ÙĬد
    0.06
    ,cp
    0.06
    idia
    0.06
    Activations Density 0.000%

    No Known Activations