© 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. 78608
    Prev
    Next
    INDEX
    Explanations

    words and phrases that convey concepts of relationships, support, and emotional connections

    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
     NAT
    -0.07
    kud
    -0.07
    üt
    -0.07
    avigator
    -0.06
    pras
    -0.06
    Raised
    -0.06
     camp
    -0.06
    á»Ń
    -0.06
    shan
    -0.06
     rais
    -0.06
    POSITIVE LOGITS
    064
    0.07
     اÙĦÙĪص
    0.07
     Sentinel
    0.06
    é³
    0.06
    оÑĤа
    0.06
     Ùħرک
    0.06
     Hoover
    0.06
     Ov
    0.06
     surve
    0.06
    алÑĥ
    0.06
    Activations Density 0.001%

    No Known Activations