© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58434
    Prev
    Next
    INDEX
    Explanations

    phrases related to health and social impact discussions

    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
     rozp
    -0.07
    ç®±
    -0.07
    _REPLACE
    -0.07
     oppon
    -0.07
    .getSelection
    -0.07
    gran
    -0.07
    ä¹ħä¹ħ
    -0.07
    à¹Īำ
    -0.07
     reluct
    -0.06
    ">ÃĹ</
    -0.06
    POSITIVE LOGITS
     capacity
    0.15
     Capacity
    0.13
    Capacity
    0.13
     strain
    0.13
     overloaded
    0.12
    capacity
    0.12
     strains
    0.12
     overload
    0.12
     burden
    0.11
     overcrow
    0.11
    Activations Density 0.186%

    No Known Activations