© 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. 3738
    Prev
    Next
    INDEX
    Explanations

    names and roles related to sound design and editing professionals

    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
    ikal
    -0.08
    ensex
    -0.07
    íħIJ
    -0.07
     Åŀah
    -0.07
    untas
    -0.07
    iÄĩ
    -0.07
    ÑĦÑĤ
    -0.07
    wat
    -0.07
    ÄĽle
    -0.07
    åŁ
    -0.07
    POSITIVE LOGITS
    Effects
    0.06
     param
    0.06
     effects
    0.06
     Effects
    0.06
    Editing
    0.06
    utomation
    0.06
     per
    0.05
    ARR
    0.05
    ances
    0.05
     Jan
    0.05
    Activations Density 0.010%

    No Known Activations