© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 78575
    Prev
    Next
    INDEX
    Explanations

    elements related to classification and organization of information

    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
     çal
    -0.06
    etu
    -0.06
    esser
    -0.05
     Census
    -0.05
    æ´»åĬ¨
    -0.05
    eca
    -0.05
     Statistics
    -0.05
     Stats
    -0.05
    .statistics
    -0.05
     bout
    -0.05
    POSITIVE LOGITS
     table
    0.14
     Table
    0.12
     chart
    0.11
    -table
    0.11
    table
    0.11
    Table
    0.11
    _table
    0.10
     tables
    0.10
    .table
    0.10
     tabel
    0.10
    Activations Density 0.022%

    No Known Activations