© 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. 57317
    Prev
    Next
    INDEX
    Explanations

    phrases indicating affiliations to cultural institutions or artistic entities

    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
    deo
    -0.08
    tober
    -0.07
    xD
    -0.07
    gan
    -0.07
    -ts
    -0.07
    xA
    -0.06
    ear
    -0.06
    pedo
    -0.06
    ifax
    -0.06
    volution
    -0.06
    POSITIVE LOGITS
    \application
    0.06
    'gc
    0.06
    cház
    0.06
    vecs
    0.06
    URLException
    0.06
     Depos
    0.06
     Ports
    0.06
    ayı
    0.06
     Scalars
    0.06
    ë§Į
    0.06
    Activations Density 0.018%

    No Known Activations