© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71130
    Prev
    Next
    INDEX
    Explanations

    references to nuanced interactions and relationships between people and situations

    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
    $__
    -0.08
    ÑģоÑĢ
    -0.08
    irit
    -0.07
    ---</
    -0.07
    ocalypse
    -0.07
    ogl
    -0.07
    جاÙħ
    -0.07
    èªĮ
    -0.07
    arius
    -0.07
     seins
    -0.07
    POSITIVE LOGITS
    bos
    0.08
     events
    0.08
     people
    0.07
     individuals
    0.07
     important
    0.06
     persons
    0.06
     phenomena
    0.06
    reff
    0.06
     particular
    0.06
     abstract
    0.06
    Activations Density 0.036%

    No Known Activations