© 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. 55712
    Prev
    Next
    INDEX
    Explanations

    status updates and control commands in code

    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
     Redistributions
    -0.07
    olit
    -0.07
     InitializeComponent
    -0.07
    ابت
    -0.07
    elli
    -0.06
    apter
    -0.06
     Freed
    -0.06
     оÑĤвеÑĢ
    -0.06
     sez
    -0.06
    erner
    -0.06
    POSITIVE LOGITS
    /current
    0.07
    cko
    0.07
    ahren
    0.07
    /original
    0.07
    ÑĢек
    0.07
    åijĬ
    0.06
    ichern
    0.06
    quo
    0.06
    TY
    0.06
     Old
    0.06
    Activations Density 0.089%

    No Known Activations