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. 95808
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and notable figures

    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
     onCancelled
    -0.07
    stit
    -0.07
    mpar
    -0.07
    ollectors
    -0.07
    staw
    -0.07
    ifold
    -0.06
    Quiet
    -0.06
    vatel
    -0.06
    estro
    -0.06
     Trustees
    -0.06
    POSITIVE LOGITS
     bul
    0.07
     and
    0.07
    å¡
    0.07
     dub
    0.06
     Bul
    0.06
     GÃľ
    0.06
    erville
    0.06
     point
    0.06
     sheer
    0.06
    ãģ£ãģ
    0.06
    Activations Density 0.163%

    No Known Activations