© 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. 126035
    Prev
    Next
    INDEX
    Explanations

    references to conflict and insecurity involving groups and territories

    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
    onya
    -0.08
    trag
    -0.07
    uw
    -0.07
    _featured
    -0.07
    Compression
    -0.07
    ONA
    -0.06
    bedo
    -0.06
    ÄĻ
    -0.06
     authorities
    -0.06
    oeff
    -0.06
    POSITIVE LOGITS
     protesters
    0.08
     protestors
    0.08
     criticism
    0.08
     demands
    0.07
     protester
    0.07
    cope
    0.07
     protests
    0.07
     demonstrators
    0.07
     protest
    0.06
     grassroots
    0.06
    Activations Density 0.054%

    No Known Activations