© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27508
    Prev
    Next
    INDEX
    Explanations

    references to specific programs and initiatives related to youth development and community building

    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
    oles
    -0.07
     strr
    -0.06
     strtok
    -0.06
    689
    -0.06
    azer
    -0.06
    Ñħи
    -0.06
    ivi
    -0.06
     ÐĶоб
    -0.06
    ainty
    -0.06
    OLS
    -0.06
    POSITIVE LOGITS
    -lite
    0.07
    iteDatabase
    0.07
    .house
    0.06
     House
    0.06
    comic
    0.06
    aska
    0.06
    .cf
    0.06
    porno
    0.06
    postalcode
    0.06
     ideas
    0.06
    Activations Density 0.000%

    No Known Activations