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. 5064
    Prev
    Next
    INDEX
    Explanations

    statistical terms and calculations related to data analysis

    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
    iva
    -0.08
    )prepare
    -0.07
    dorf
    -0.07
    /rfc
    -0.07
    apr
    -0.07
    lice
    -0.07
    OVE
    -0.07
     çī
    -0.07
    orf
    -0.07
     EXEMPLARY
    -0.07
    POSITIVE LOGITS
    olle
    0.07
    bero
    0.06
     unc
    0.05
     sympt
    0.05
    اء
    0.05
     real
    0.05
    ÏĮÏģ
    0.05
    -Smith
    0.05
     emp
    0.05
    alerts
    0.05
    Activations Density 0.025%

    No Known Activations