© 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. 22-LLAMASCOPE-RES-131K
    11. 4276
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and innovation in a socio-political 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
    ritt
    -0.07
    Dispose
    -0.07
    898
    -0.07
    /browse
    -0.07
    iska
    -0.07
    ãģ¨ãģĦ
    -0.07
    é¬
    -0.06
    IRT
    -0.06
    æ³ī
    -0.06
    illo
    -0.06
    POSITIVE LOGITS
     Peace
    0.09
    Peace
    0.08
     peace
    0.07
     laws
    0.07
     law
    0.07
     Laws
    0.07
     Global
    0.07
     power
    0.07
    laws
    0.07
    isex
    0.07
    Activations Density 0.000%

    No Known Activations