© 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. 17-LLAMASCOPE-RES-131K
    11. 86894
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism and opposition to projects or actions

    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
    ello
    -0.08
     Záp
    -0.07
    tas
    -0.07
    ÑĥÑĢи
    -0.07
    fte
    -0.06
    ÐłÐĺ
    -0.06
    ÐłÐĿ
    -0.06
    овÑĭй
    -0.06
     Verde
    -0.06
    /Dk
    -0.06
    POSITIVE LOGITS
    bach
    0.07
    edBy
    0.07
    717
    0.07
    agues
    0.06
    voice
    0.06
    ãĥ¼ãĥģ
    0.06
    voices
    0.06
    887
    0.06
    Duplicates
    0.06
    prec
    0.06
    Activations Density 0.041%

    No Known Activations