© 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. 9-LLAMASCOPE-RES-131K
    11. 95343
    Prev
    Next
    INDEX
    Explanations

    references to harmful chemicals and their usage in society

    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
    meldung
    -0.07
    боÑĢ
    -0.06
    zt
    -0.06
     dummy
    -0.06
    ullo
    -0.06
    asiswa
    -0.06
     nick
    -0.06
    obb
    -0.06
    icorn
    -0.06
    aint
    -0.06
    POSITIVE LOGITS
    çģŃ
    0.06
    Å¡ak
    0.06
    ADDE
    0.06
    063
    0.06
    915
    0.06
    HTTPHeader
    0.06
     Slate
    0.06
    ãĥ¼ãĥ«
    0.06
     TMPro
    0.06
    ACHI
    0.06
    Activations Density 0.015%

    No Known Activations