© 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. 56403
    Prev
    Next
    INDEX
    Explanations

    references to families and their living conditions

    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
    oÄŁ
    -0.08
    ëĨį
    -0.08
    ãn
    -0.08
    евиÑĩ
    -0.08
    ÑĢÑĥÑĩ
    -0.07
    .listView
    -0.07
    æľį
    -0.07
    ön
    -0.07
    \<^
    -0.07
    upy
    -0.07
    POSITIVE LOGITS
    607
    0.07
    /groups
    0.07
    rist
    0.06
    803
    0.06
    estic
    0.06
    889
    0.06
    rosse
    0.06
    æĵį
    0.06
    216
    0.06
     families
    0.06
    Activations Density 0.011%

    No Known Activations