© 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. 94285
    Prev
    Next
    INDEX
    Explanations

    phrases focused on initiatives and actions aimed at improvement and support for community health and safety

    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
     Ampl
    -0.07
     amel
    -0.06
     ampl
    -0.06
     fret
    -0.06
    aku
    -0.06
     escal
    -0.06
    Ì
    -0.06
    olie
    -0.06
    é¼»
    -0.06
    crew
    -0.06
    POSITIVE LOGITS
    better
    0.07
     improve
    0.07
     better
    0.07
    ius
    0.07
     improving
    0.07
    ocale
    0.07
    Address
    0.07
    ultur
    0.07
     improved
    0.06
     hol
    0.06
    Activations Density 0.036%

    No Known Activations