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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40372
    Prev
    Next
    INDEX
    Explanations

    names of individuals and references to specific people

    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
    thon
    -0.06
    iani
    -0.06
    ÏĦικο
    -0.06
    arness
    -0.06
    glas
    -0.06
    poÄį
    -0.06
     Ø´Ùħ
    -0.06
     intervention
    -0.05
    cope
    -0.05
    гл
    -0.05
    POSITIVE LOGITS
    /gtest
    0.07
     STYLE
    0.07
    ritel
    0.07
     kür
    0.07
    ãĥ¼ãĥģ
    0.07
    xima
    0.07
    pii
    0.06
    oucher
    0.06
     Inst
    0.06
    peech
    0.06
    Activations Density 0.016%

    No Known Activations