© 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. 9-LLAMASCOPE-RES-131K
    11. 98457
    Prev
    Next
    INDEX
    Explanations

    references to New Zealand and its associated contexts or characteristics

    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
    ader
    -0.08
    addin
    -0.07
    aders
    -0.06
     Panda
    -0.06
    &E
    -0.06
     Bernstein
    -0.06
    elerik
    -0.06
    ado
    -0.06
    pos
    -0.06
     sch
    -0.06
    POSITIVE LOGITS
    anders
    0.09
    /New
    0.07
    _ln
    0.07
    orio
    0.07
    ahlen
    0.07
    ers
    0.07
    328
    0.07
    /world
    0.07
    اÛĮÛĮ
    0.07
    à¹ģลà¸Ļà¸Ķ
    0.07
    Activations Density 0.008%

    No Known Activations