© 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. 106551
    Prev
    Next
    INDEX
    Explanations

    institutions and organizations related to arts and education

    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
    ÑĢоÑģÑĤ
    -0.07
     ham
    -0.06
    WithError
    -0.06
     resent
    -0.06
     inaugural
    -0.06
    arra
    -0.06
    åı£
    -0.06
    emens
    -0.06
     Pix
    -0.05
    Iron
    -0.05
    POSITIVE LOGITS
     nonprofit
    0.07
    achat
    0.07
    è¡ĵ
    0.07
    aea
    0.07
    ajas
    0.07
    neum
    0.07
     Fell
    0.07
    erness
    0.07
    otu
    0.07
    GuidId
    0.06
    Activations Density 0.016%

    No Known Activations