© 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. 127472
    Prev
    Next
    INDEX
    Explanations

    phrases expressing preference or comparison

    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
    utan
    -0.07
    iddet
    -0.07
    ãĤ¤ãĤº
    -0.07
    modal
    -0.07
    ož
    -0.06
    ritos
    -0.06
    ạt
    -0.06
    ấu
    -0.06
    Accessibility
    -0.06
    achen
    -0.06
    POSITIVE LOGITS
    able
    0.07
    nor
    0.06
     nor
    0.06
    licative
    0.06
     having
    0.06
    uan
    0.06
    owitz
    0.06
    ABLE
    0.06
    Nor
    0.06
    μι
    0.06
    Activations Density 0.005%

    No Known Activations