© 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. 17-LLAMASCOPE-RES-131K
    11. 74191
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significance or implications

    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
    oleon
    -0.08
    olumn
    -0.08
    thus
    -0.07
    BuilderFactory
    -0.07
    arlo
    -0.07
    rah
    -0.07
    nier
    -0.07
    >this
    -0.07
    ausal
    -0.07
    ระà¹Ģà¸ļ
    -0.07
    POSITIVE LOGITS
     having
    0.07
     taking
    0.07
     resort
    0.07
     re
    0.06
     USS
    0.06
     us
    0.06
     use
    0.06
     a
    0.06
    auge
    0.05
    inges
    0.05
    Activations Density 0.013%

    No Known Activations