Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95777
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to music and performance

    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
    oci
    -0.07
    aden
    -0.07
    ess
    -0.07
    onis
    -0.06
     nok
    -0.06
     Hoa
    -0.06
    actable
    -0.06
    brig
    -0.06
    à¥įरथ
    -0.06
    .UserInfo
    -0.06
    POSITIVE LOGITS
    Äħż
    0.07
    anean
    0.07
     commun
    0.06
     compared
    0.06
    webdriver
    0.05
    asta
    0.05
     anzeigen
    0.05
    osate
    0.05
    roken
    0.05
    ÃŃstica
    0.05
    Activations Density 0.067%

    No Known Activations