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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 57833
    Prev
    Next
    INDEX
    Explanations

    phrases that involve the action of 'putting' something in place or context

    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
    hani
    -0.08
    veau
    -0.07
    jn
    -0.07
    iae
    -0.07
     zorunda
    -0.07
    à¤łà¤¨
    -0.06
    гоÑĢод
    -0.06
    .openg
    -0.06
    llib
    -0.06
    _ops
    -0.06
    POSITIVE LOGITS
     otherwise
    0.08
     OTHERWISE
    0.07
     Otherwise
    0.07
    puts
    0.07
     Abstract
    0.06
    aret
    0.06
    Abstract
    0.06
     principles
    0.06
     theory
    0.06
    atively
    0.06
    Activations Density 0.016%

    No Known Activations