© 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. 93976
    Prev
    Next
    INDEX
    Explanations

    references to apartments and related living spaces

    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
    qing
    -0.07
    ìļ´ëį°
    -0.07
     presence
    -0.06
    sdale
    -0.06
    aims
    -0.06
    ucursal
    -0.06
    uxtap
    -0.06
    åŁŁ
    -0.06
    ymb
    -0.06
    gart
    -0.06
    POSITIVE LOGITS
    /table
    0.08
     dwell
    0.07
    Ø´ÙĨ
    0.07
    illary
    0.07
    dad
    0.07
    à¥Ģय
    0.07
    ssh
    0.07
    stract
    0.07
    -style
    0.06
    arent
    0.06
    Activations Density 0.005%

    No Known Activations