© 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 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. 71336
    Prev
    Next
    INDEX
    Explanations

    phrases related to caution or advisories

    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
    bane
    -0.07
    lette
    -0.07
    /basic
    -0.06
    ç¹ģ
    -0.06
    mith
    -0.06
    villa
    -0.06
    æı
    -0.06
    cket
    -0.06
    _VO
    -0.06
    AVE
    -0.06
    POSITIVE LOGITS
     any
    0.12
    ä»»ä½ķ
    0.09
     qualquer
    0.09
    Any
    0.08
     Any
    0.08
     ANY
    0.07
    -any
    0.07
     cualquier
    0.07
     anything
    0.07
     use
    0.07
    Activations Density 0.006%

    No Known Activations