© 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. 16397
    Prev
    Next
    INDEX
    Explanations

    references to news agencies or contributors in articles

    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
    ogui
    -0.07
    nap
    -0.06
    awah
    -0.06
    usat
    -0.06
    izoph
    -0.06
    аÑĢÑĩ
    -0.06
    zial
    -0.06
    รว
    -0.06
    entric
    -0.06
    595
    -0.06
    POSITIVE LOGITS
    affen
    0.07
    rys
    0.07
    ¿
    0.07
    ầu
    0.06
    swer
    0.06
     addCriterion
    0.06
    ebi
    0.06
    emento
    0.06
    eya
    0.06
    à¹Īาà¸Ħ
    0.06
    Activations Density 0.000%

    No Known Activations