© 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. 9-LLAMASCOPE-RES-131K
    11. 95722
    Prev
    Next
    INDEX
    Explanations

    references to orchestras and conductors

    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
    .Dependency
    -0.09
    ctype
    -0.08
    аза
    -0.07
    _RB
    -0.07
    ampa
    -0.07
     gest
    -0.07
    dbName
    -0.07
    енÑģ
    -0.07
     Gest
    -0.07
    ascript
    -0.07
    POSITIVE LOGITS
    abin
    0.06
     Yue
    0.06
    enge
    0.06
     Various
    0.06
    auth
    0.06
    ffield
    0.06
    aben
    0.06
     Bath
    0.05
    807
    0.05
    mem
    0.05
    Activations Density 0.020%

    No Known Activations