© 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. 94081
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conflict or opposition

    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
    /Dk
    -0.08
    erde
    -0.08
     jenter
    -0.08
    ourcem
    -0.08
    chez
    -0.08
    stanov
    -0.08
    ALAR
    -0.08
    .liferay
    -0.07
    lid
    -0.07
    меÑĤÑĮ
    -0.07
    POSITIVE LOGITS
     against
    0.10
     competing
    0.09
     Compet
    0.08
     factions
    0.08
    against
    0.07
     two
    0.07
     Against
    0.07
     rival
    0.07
     forces
    0.06
     powerful
    0.06
    Activations Density 0.026%

    No Known Activations