© 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. 76047
    Prev
    Next
    INDEX
    Explanations

    mentions of businesses and companies

    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
    ondon
    -0.07
    panse
    -0.07
    adesh
    -0.07
     Sour
    -0.06
    dens
    -0.06
    cx
    -0.06
    lam
    -0.06
    ensi
    -0.06
    оÑģÑĤÑĥп
    -0.06
    eya
    -0.06
    POSITIVE LOGITS
    ÎķÎļ
    0.07
    ieri
    0.06
    Ñģка
    0.06
     ÑĤов
    0.06
    _firestore
    0.06
     Rosenberg
    0.06
    uggy
    0.06
    ula
    0.06
    ίκ
    0.06
    noon
    0.06
    Activations Density 0.002%

    No Known Activations