© 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. 55855
    Prev
    Next
    INDEX
    Explanations

    references to different types of relationships and their complexities

    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
     unified
    -0.08
    utex
    -0.07
    aniem
    -0.06
    çµ±
    -0.06
     گرد
    -0.06
    _BITMAP
    -0.06
    stud
    -0.06
    Ľå»º
    -0.06
    /Create
    -0.06
    .ali
    -0.06
    POSITIVE LOGITS
    ationship
    0.07
     relationships
    0.07
     relationship
    0.07
     dynamics
    0.07
    åħ³ç³»
    0.06
    asca
    0.06
     ship
    0.06
     between
    0.06
    hest
    0.06
     formed
    0.06
    Activations Density 0.049%

    No Known Activations