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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 104312
    Prev
    Next
    INDEX
    Explanations

    phrases indicating environmental aspects or sustainability in contexts involving government and market strategies

    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
    Ñģм
    -0.07
    егоÑĢ
    -0.07
     shl
    -0.07
    FRING
    -0.07
    ãĥ»ãĥ»ãĥ»↵↵
    -0.07
     hete
    -0.07
    è¡
    -0.06
    æĹıèĩªæ²»
    -0.06
    ↵↵
    -0.06
    ustil
    -0.06
    POSITIVE LOGITS
    cn
    0.06
    rs
    0.06
     McMahon
    0.06
    ROID
    0.06
    antro
    0.06
    isz
    0.06
    owa
    0.06
    icht
    0.06
    ROY
    0.06
    925
    0.06
    Activations Density 0.031%

    No Known Activations